Tables serve as a core format for representing structured data on the web, as their two-dimensional layouts effectively encode complex inter-entity relationships. However, real-world web tables often feature heterogeneous structures and rich semantics. Accurately interpreting such tables requires not only spatial layout perception but also multi-step reasoning across rows and columns, posing substantial challenges to web intelligence systems. Multimodal large language models (MLLMs) show promise in table question answering (TableQA) by leveraging visual layouts. However, their performance on complex web tables remains uneven, as existing benchmarks often blur the impact of individual difficulty factors, hindering precise capability analysis. To advance TableQA beyond superficial task difficulty and toward interpretable capability modeling, we introduce MMTableBench, a multi-level benchmark that systematically evaluates MLLMs along two fine-grained dimensions: layout complexity and reasoning complexity. By organizing table-question pairs along these axes, MMTableBench facilitates a detailed evaluation of model performance under varying structural and reasoning challenges, while revealing the respective strengths and limitations of multimodal inputs. Our comprehensive analysis shows that state-of-the-art MLLMs continue to exhibit notable limitations when confronted with complex layouts and deep reasoning tasks, underscoring persistent gaps despite the structural advantages offered by visual inputs. MMTableBench thus provides not only a rigorous evaluation framework but also a diagnostic tool for analyzing and interpreting model behaviors, enabling more transparent and explainable progress in multimodal TableQA development.

Searchable symmetric encryption (SSE) enables the storage and retrieval of encrypted data on untrusted cloud servers, while dynamic searchable symmetric encryption (DSSE) further supports updating encrypted data. To date, in multi-user environments, most DSSE schemes cannot achieve simultaneous access control for both keyword retrieval and data updates. To address this issue, we propose a new DSSE scheme with efficient and complete(keyword retrieval and update)access control for multi-user environments, named EFCAM. Our work has simultaneously achieved efficient, flexible, and fine-grained access control for keyword retrieval and updating, this is extremely rare in existing research. For update operations, we combine file index encoding and homomorphic encryption (HE) technology, so that EFCAM optimizes the calculation; to achieve flexible access control, we adopt an equality test scheme that can supports three types of update authorization. For retrieval operations, users do not need to share keys. By executing a single query, the users can effectively retrieve all the data that they have permission to access. To enhance system security and operational efficiency, we have extended EFCAM with a dynamic policy update mechanism for flexible and real-time adjustment of access control policies. We formally analyze the security of EFCAM to prove that our scheme has forward security (FS) and backward security (BS). Experimental results show that, EFCAM maintains outstanding efficiency in encrypted data retrieval and update operations within multi-user environments, while also exhibiting strong scalability.

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do not exist in the image. In this paper, we reveal that object hallucination can be attributed to overconfidence in irrelevant visual features when soft visual tokens map to the LLM's word embedding space. Specifically, by figuring out the semantic similarity between visual tokens and LLM's word embedding, we observe that the smoothness of similarity distribution strongly correlates with the emergence of object hallucinations. To mitigate hallucinations, we propose using the Variational Information Bottleneck (VIB) to alleviate overconfidence by introducing stochastic noise, facilitating the constraining of irrelevant information. Furthermore, we propose an entropy-based noise-controlling strategy to enable the injected noise to be adaptively constrained regarding the smoothness of the similarity distribution. We adapt the proposed AdaVIB across distinct model architectures. Experimental results demonstrate that the proposed AdaVIB mitigates object hallucinations by effectively alleviating the overconfidence in irrelevant visual features, with consistent improvements on two object hallucination benchmarks.

Chain-of-thought (CoT) has emerged as a powerful technique to elicit reasoning in large language models and improve a variety of downstream tasks. CoT mainly demonstrates excellent performance in English, but its usage in low-resource languages is constrained due to poor language generalization. To bridge the gap among different languages, we propose a cross-lingual instruction fine-tuning framework (xCoT) to transfer knowledge from high-resource languages to low-resource languages. Specifically, the multilingual instruction training data (xCoT-Instruct) is created to encourage the semantic alignment of multiple languages. We introduce cross-lingual in-context few-shot learning (xICL) to accelerate multilingual agreement in instruction tuning, where some fragments of source languages in examples are randomly substituted by their counterpart translations of target languages. During multilingual instruction tuning, we adopt the randomly online CoT strategy to enhance the multilingual reasoning ability of the large language model by first translating the query to another language and then answering in English. To further facilitate the language transfer, we leverage the high-resource CoT to supervise the training of low-resource languages with cross-lingual distillation. Experimental results demonstrate the superior performance of xCoT in reducing the gap among different languages, highlighting its potential to reduce the cross-lingual gap.

Recent advancements in Large Language Models (LLMs) have markedly enhanced the interpretation and processing of tabular data, introducing previously unimaginable capabilities. Despite these achievements, LLMs still encounter significant challenges when applied in industrial scenarios, particularly due to the increased complexity of reasoning required with real-world tabular data, underscoring a notable disparity between academic benchmarks and practical applications. To address this discrepancy, we conduct a detailed investigation into the application of tabular data in industrial scenarios and propose a comprehensive and complex benchmark TableBench, including 18 fields within four major categories of table question answering (TableQA) capabilities. Furthermore, we introduce TableLLM, trained on our meticulously constructed training set TableInstruct, achieving comparable performance with GPT-3.5. Massive experiments conducted on TableBench indicate that both open-source and proprietary LLMs still have significant room for improvement to meet real-world demands, where the most advanced model, GPT-4, achieves only a modest score compared to humans.

Emotional development of children fundamentally relies on secure attachment relationships, yet current AI companions lack the theoretical foundation to provide developmentally appropriate emotional support. We introduce DinoCompanion, the first attachment-theory-grounded multimodal robot for emotionally responsive child-AI interaction. We address three critical challenges in child-AI systems: the absence of developmentally-informed AI architectures, the need to balance engagement with safety, and the lack of standardized evaluation frameworks for attachment-based capabilities. Our contributions include: (i) a multimodal dataset of 128 caregiver-child dyads containing 125,382 annotated clips with paired preference-risk labels, (ii) CARPO (Child-Aware Risk-calibrated Preference Optimization), a novel training objective that maximizes engagement while applying epistemic-uncertainty-weighted risk penalties, and (iii) AttachSecure-Bench, a comprehensive evaluation benchmark covering ten attachment-centric competencies with strong expert consensus. AttachSecure-Bench achieves state-of-the-art performance (57.15%), outperforming GPT-4o and Gemini-2.5-Pro, with exceptional secure base behaviors and superior attachment risk detection. Ablations validate the critical importance of multimodal fusion, uncertainty-aware risk modeling, and hierarchical memory for coherent, emotionally attuned interactions.

As interest in using Large Language Models for interactive and emotionally rich experiences grows, virtual pet companionship emerges as a novel yet underexplored application. Existing approaches focus on basic pet role-playing interactions without systematically benchmarking LLMs for comprehensive companionship. In this paper, we introduce PET-BENCH, a dedicated benchmark that evaluates LLMs across both self-interaction and human-interaction dimensions. Unlike prior work, PET-BENCH emphasizes self-evolution and developmental behaviors alongside interactive engagement, offering a more realistic reflection of pet companionship. It features diverse tasks such as intelligent scheduling, memory-based dialogues, and psychological conversations, with over 7,500 interaction instances designed to simulate pet behaviors. Evaluation of 28 LLMs reveals significant performance variations linked to model size and inherent capabilities, underscoring the need for specialized optimization in this domain. PET-BENCH serves as a foundational resource for benchmarking pet-related LLM abilities and advancing emotionally immersive human-pet interactions.

In the domain of Document AI, parsing semi-structured image form is a crucial Key Information Extraction (KIE) task. The advent of pre-trained multimodal models significantly empowers Document AI frameworks to extract key information from form documents in different formats such as PDF, Word, and images. Nonetheless, form parsing is still encumbered by notable challenges like subpar capabilities in multilingual parsing and diminished recall in industrial contexts in rich text and rich visuals. In this work, we introduce a simple but effective Multimodal and Multilingual semi-structured FORM PARSER (XFormParser), which is anchored on a comprehensive Transformer-based pre-trained language model and innovatively amalgamates semantic entity recognition (SER) and relation extraction (RE) into a unified framework. Combined with Bi-LSTM, the performance of multilingual parsing is significantly improved. Furthermore, we develop InDFormSFT, a pioneering supervised fine-tuning (SFT) industrial dataset that specifically addresses the parsing needs of forms in a variety of industrial contexts. Through rigorous testing on established benchmarks, XFormParser has demonstrated its unparalleled effectiveness and robustness. Compared to existing state-of-the-art (SOTA) models, XFormParser notably achieves up to 1.79% F1 score improvement on RE tasks in language-specific settings. It also exhibits exceptional improvements in cross-task performance in both multilingual and zero-shot settings.

Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on “huge” databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To address these challenges, we introduce MAC-SQL, a novel LLM-based multi-agent collaborative framework. Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries. The decomposer agent collaborates with auxiliary agents, which are activated as needed and can be expanded to accommodate new features or tools for effective Text-to-SQL parsing. In our framework, We initially leverage GPT-4 as the strong backbone LLM for all agent tasks to determine the upper bound of our framework. We then fine-tune an open-sourced instruction-followed model, SQL-Llama, by leveraging Code Llama 7B, to accomplish all tasks as GPT-4 does. Experiments show that SQL-Llama achieves a comparable execution accuracy of 43.94, compared to the baseline accuracy of 46.35 for vanilla GPT-4. At the time of writing, MAC-SQL+GPT-4 achieves an execution accuracy of 59.59 when evaluated on the BIRD benchmark, establishing a new state-of-the-art (SOTA) on its holdout test set.

Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Incorporating external knowledge into dialogue generation (DG) is crucial for enhancing response accuracy, where evidence fragments serve as effective knowledgeable snippets that support factual dialogue replies. However, introducing irrelevant content beyond valid knowledge fragments can adversely affect reply quality and lead to hallucinated responses. Prior work relies on manual annotations to develop models for identifying evidence within external knowledge. However, these annotations often cover only a limited portion of the valid evidence, restricting the ability of models to mine useful evidence from retrieved knowledge. To fully Unleash the potential of evidence, we propose a framework to effectively incorporate Evidence in knowledge-Intensive Dialogue Generation (U-EIDG). Specifically, we develop an evidence miner (Evid-M) that harnesses the power of large language models (LLMs) to mine reliable evidence labels from external knowledge. Subsequently, we propose an evidence indicator (Evid-I) to effectively identify valid evidence from retrieved knowledge by utilizing these evidence labels. Furthermore, we introduce an evidence-augmented generator (EAG) incorporating an evidence-attention mechanism that enables the model to focus on segments supported by evidence. Experimental results on the MultiDoc2Dial and WoW benchmarks indicate that the proposed method significantly outperforms other baselines, with a +3∼5 points improvement in Rouge-L. Further analysis confirms the effectiveness of fully mining valid evidence fragments for knowledge-intensive dialogue generation.

Large Language Models (LLMs) have made significant strides in Natural Language Processing and coding, yet they struggle with robustness and accuracy in complex function calls. To tackle these challenges, this paper introduces ADC, an innovative approach that enhances LLMs’ ability to follow function formats and match complex parameters. ADC utilizes a high-quality code fine-tuning dataset with line-level execution feedback, providing granular process supervision that fosters strong logical reasoning and adherence to function formats. It also employs an adversarial dataset generation process to improve parameter matching. The staged training methodology capitalizes on both enriched code datasets and refined adversarial datasets, leading to marked improvements in function calling capabilities on the Berkeley Function-Calling Leaderboard (BFCL) Benchmark. The innovation of ADC lies in its strategic combination of process supervision, adversarial refinement, and incremental learning, setting a new standard for LLM proficiency in complex function calling.

The increasing application of multi-modal large language models (MLLMs) across various sectors have spotlighted the essence of their output reliability and accuracy, particularly their ability to produce content grounded in factual information (e.g. common and domain-specific knowledge). In this work, we introduce SimpleVQA, the first comprehensive multi-modal benchmark to evaluate the factuality ability of MLLMs to answer natural language short questions. SimpleVQA is characterized by six key features: it covers multiple tasks and multiple scenarios, ensures high quality and challenging queries, maintains static and timeless reference answers, and is straightforward to evaluate. Our approach involves categorizing visual question-answering items into 9 different tasks around objective events or common knowledge and situating these within 9 topics. Rigorous quality control processes are implemented to guarantee high-quality, concise, and clear answers, facilitating evaluation with minimal variance via an LLM-as-a-judge scoring system. Using SimpleVQA, we perform a comprehensive assessment of leading 18 MLLMs and 8 text-only LLMs, delving into their image comprehension and text generation abilities by identifying and analyzing error cases.

We introduce UnrealZoo, a collection of over 100 photo-realistic 3D virtual worlds built on Unreal Engine, designed to reflect the complexity and variability of open-world environments. We also provide a rich variety of playable entities, including humans, animals, robots, and vehicles for embodied AI research. We extend UnrealCV with optimized APIs and tools for data collection, environment augmentation, distributed training, and benchmarking. These improvements achieve significant improvements in the efficiency of rendering and communication, enabling advanced applications such as multi-agent interactions. Our experimental evaluation across visual navigation and tracking tasks reveals two key insights: 1) environmental diversity provides substantial benefits for developing generalizable reinforcement learning (RL) agents, and 2) current embodied agents face persistent challenges in open-world scenarios, including navigation in unstructured terrain, adaptation to unseen morphologies, and managing latency in the close-loop control systems for interacting in highly dynamic objects. UnrealZoo thus serves as both a comprehensive testing ground and a pathway toward developing more capable embodied AI systems for real-world deployment.

Code large language models (LLMs) have shown remarkable advances in code understanding, completion, and generation tasks. Programming benchmarks, comprised of a selection of code challenges and corresponding test cases, serve as a standard to evaluate the capability of different LLMs in such tasks. However, most existing benchmarks primarily focus on Python and are still restricted to a limited number of languages, where other languages are translated from the Python samples degrading the data diversity. To further facilitate the research of code LLMs, we propose a massively multilingual code benchmark covering 40 programming languages (McEval) with 16K test samples, which substantially pushes the limits of code LLMs in multilingual scenarios. The benchmark contains challenging code completion, understanding, and generation evaluation tasks with finely curated massively multilingual instruction corpora McEval-Instruct. In addition, we introduce an effective multilingual coder mCoder trained on McEval-Instruct to support multilingual programming language generation. Extensive experimental results on McEval show that there is still a difficult journey between open-source models and closed-source LLMs in numerous languages. The instruction corpora and evaluation benchmark are available at https://github.com/MCEVAL/McEval.

With the rapid advancement of Social Networking Services (SNS), the need for intelligent and efficient interaction within diverse platforms has become more crucial. Large Language Models (LLMs) play an important role in SNS as they possess the potential to revolutionize user experience, content generation, and communication dynamics. However, recent studies focus on isolated SNS tasks rather than a comprehensive evaluation. In this paper, we introduce SNS-Bench, specially constructed for assessing the abilities of large language models from different Social Networking Services, with a wide range of SNS-related information. SNS-Bench encompasses 8 different tasks such as note classification, query content relevance, and highlight words generation in comments. Finally, 6,658 questions of social media text, including subjective questions, single-choice, and multiple-choice questions, are concluded in SNS-Bench. Further, we evaluate the performance of over 25+ current diverse LLMs on our SNS-Bench. Models with different sizes exhibit performance variations, yet adhere to the scaling law. Moreover, we hope provide more insights to revolutionize the techniques of social network services with LLMs.

In recent years, the advancements of Large Language Models (LLMs) have enhanced human-AI interactions and memory systems, but their event results tend to be general and weak in differentiation, which will bring high-impact event results. These factors are crucial for risk assessment and decision-making. Therefore, we introduce the Informativeness-Driven Memory Mechanism (IDMM), which assesses results based on their complexity, uniqueness, and potential future impact to prioritize important memories. The IDMM continuously evaluates and adjusts the strength of memories, reinforcing critical events while allowing less informative ones to decay. This dynamic memory management system is integrated into the ShannonGuard agent, which demonstrates a 20% improvement in event recall accuracy, a 15% increase in memory persistence, and a 10-18% boost in decision-making effectiveness across multilingual environments. As a result, the approach of IDMM holds promise for domains that require handling rare, high-stakes events, offering broad applicability in adaptive memory retention.

We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our approach combines the off-the-shelf active tracking methods with VLMs’ reasoning capabilities, deploying a fast visual policy for normal tracking and activating VLM reasoning only upon failure detection. The framework features a memory-augmented self-reflection mechanism that enables the VLM to progressively improve by learning from past experiences, effectively addressing VLMs’ limitations in 3D spatial reasoning. Experimental results demonstrate significant performance improvements, with our framework boosting success rates by 72% with state-of-the-art RL-based approaches and 220% with PID-based methods in challenging environments. This work represents the first integration of VLM-based reasoning to assist EVT agents in proactive failure recovery, offering substantial advances for real-world robotic applications that require continuous target monitoring in dynamic, unstructured environments. Project website: https://sites.google.com/view/evt-recovery-assistant.

Recent advancements in large language models (LLMs) underscore the need for more comprehensive evaluation methods to accurately assess their reasoning capabilities. Existing benchmarks are often domain-specific and thus cannot fully capture an LLM’s general reasoning potential. To address this limitation, we introduce the **Knowledge Orthogonal Reasoning Gymnasium (KORGym)**, a dynamic evaluation platform inspired by KOR-Bench and Gymnasium. KORGym offers over fifty games in either textual or visual formats and supports interactive, multi-turn assessments with reinforcement learning scenarios. Using KORGym, we conduct extensive experiments on 19 LLMs and 8 VLMs, revealing consistent reasoning patterns within model families and demonstrating the superior performance of closed-source models. Further analysis examines the effects of modality, reasoning strategies, reinforcement learning techniques, and response length on model performance. We expect KORGym to become a valuable resource for advancing LLM reasoning research and developing evaluation methodologies suited to complex, interactive environments.

Abstract Automatic exploit generation (AEG) refers to the process of automatically finding the path in the program that can trigger vulnerabilities and generate exploits. Typically, the process of finding vulnerabilities requires fuzzing and symbolic execution techniques. The existing AEG usually sets the preset environment ideally, which does not enable all protection mechanisms. This environment is not universally applicable in actual attacks. In the newest version of GCC, the default compilation configuration has enabled all protection mechanisms. In response to this situation, we propose an exploit generation system Protection Bypass Automatic Exploit Generator (PBAEG) which automatically detects some types of stack overflow vulnerabilities and format string vulnerabilities. Then PBAEG combines the above two vulnerabilities to generate exploits. PBAEG uses symbolic execution and dynamic binary analysis to find the above two vulnerabilities, adopts different exploit generation strategies for different protection mechanisms, and defeats Non-Executable, Position-Independent Executable, Canary, and Address Space Layout Randomization (ASLR) protection mechanisms. At the same time, for some difficult-to-exploit situations, advanced stack overflow exploitation methods are applied to generate exploits. Finally, we also use docker to simulate the remote environment to test the ability of PBAEG to attack the remote environment. Experiments show that PBAEG can complete the vulnerability detection and exploitation generation of 124 binary files, 22 capture-the-flag binary files, and 10 public software, which takes a shorter time than the existing AEG and covers more types of vulnerabilities. PBAEG adopts more vulnerability exploitation techniques, can generate exploits in the form of files by using pwntools, and successfully verifies the exploitations generated in the remote simulation environment.

The rapid advances in computer vision and natural language processing have led to increased attention toward the challenge of understanding vision and language together across multiple domains. Representation learning has become a major focus of research on cross-modal information understanding. However, current methods often fall short of providing comprehensive interaction and meaningful supervised guidance that would allow for effective learning of visual-linguistic joint representation. In this paper, we introduce the Breadth and Depth Attention Pre-training (BDAP) model for vision–language representation learning. Our model includes a breadth attention network designed to model feature associations between text sentences and image regions across different image levels. It uses fine-grained image features to promote more effective cross-modal feature interactions. Additionally, a depth attention network, which repeatedly calculates attention scores , is designed to deeply capture the complementarity between the image and text by gradually refining important image regions related to the text. Furthermore, we propose an attention pre-training network that leverages attention annotated distribution maps as prior knowledge to supervise the learning process of the breadth and depth attention networks, thereby enabling weight initialization of both types of attention networks. Extensive experiments on datasets of visual question answering and multi-modal sentiment analysis demonstrate the promising superiority of our BDAP model for vision–language representation learning.

American fuzzy lop (AFL), as a representative tool for fuzzing, is capable of uncovering security vulnerabilities in industrial systems. It suffers from consuming a large amount of computational resources during the mutation. To improve the performance of AFL, researchers adopt algorithms, such as particle swarm optimization and long short-term memory, to optimize mutation operator selection. However, challenges persist in these approaches integrated with AFL, including optimization model complexity, insufficient accuracy, and poor generalization scalability. To address these issues, the article proposes a new fuzzer calledDPRFuzzto optimize AFL’s mutation phases. First, in the deterministic mutation strategy mutation phase, deep Q network and trust region policy optimization are leveraged to precisely generate effective mutated samples through perceiving mutation process in a relatively short time. Then, to boost the efficiency of the Havoc random mutation phase, we improve the Thompson sampling algorithm based on a multiagent strategy to generate an overall optimal mutation strategy chain. Finally, the approach is tested on eight programs, such asreadelf,tcpdump,andnm, and the advantages ofDPRFuzzare analyzed. Most importantly, the experiment reveals results thatDPRFuzzachieves better fuzzing performance compared to the traditional and other AFL-based fuzzers, such as AFL, AFL++, AFLSmart, etc. On average,DPRFuzzachieves an improvement in code coverage of over 10%, along with a significant increase in the number of crashes.

Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios. However, previous deep models merely focused on extracting the semantics of log sequences in the same domain, leading to poor generalization on multi-domain logs. To alleviate this issue, we propose a unified Transformer-based framework for Log anomaly detection (LogFormer) to improve the generalization ability across different domains, where we establish a two-stage process including the pre-training and adapter-based tuning stage. Specifically, our model is first pre-trained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer such knowledge to the target domain via shared parameters. Besides, the Log-Attention module is proposed to supplement the information ignored by the log-paring. The proposed method is evaluated on three public datasets and one real-world dataset. Experimental results on multiple benchmarks demonstrate the effectiveness of our LogFormer with fewer trainable parameters and lower training costs.

Cross-lingual named entity recognition (CrossNER) faces challenges stemming from uneven performance due to the scarcity of multilingual corpora, especially for non-English data. While prior efforts mainly focus on data-driven transfer methods, a significant aspect that has not been fully explored is aligning both semantic and token-level representations across diverse languages. In this paper, we propose Multi-view Contrastive Learning for Cross-lingual Named Entity Recognition (MCL-NER). Specifically, we reframe the CrossNER task into a problem of recognizing relationships between pairs of tokens. This approach taps into the inherent contextual nuances of token-to-token connections within entities, allowing us to align representations across different languages. A multi-view contrastive learning framework is introduced to encompass semantic contrasts between source, codeswitched, and target sentences, as well as contrasts among token-to-token relations. By enforcing agreement within both semantic and relational spaces, we minimize the gap between source sentences and their counterparts of both codeswitched and target sentences. This alignment extends to the relationships between diverse tokens, enhancing the projection of entities across languages. We further augment CrossNER by combining self-training with labeled source data and unlabeled target data. Our experiments on the XTREME benchmark, spanning 40 languages, demonstrate the superiority of MCL-NER over prior data-driven and model-based approaches. It achieves a substantial increase of nearly +2.0 F1 scores across a broad spectrum and establishes itself as the new state-of-the-art performer.

Tao Sun, Linzheng Chai, Jian Yang, Yuwei Yin, Hongcheng Guo, Jiaheng Liu, Bing Wang, Liqun Yang, Zhoujun Li. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Shun Zhang, Yan Chaoran, Jian Yang, Jiaheng Liu, Ying Mo, Jiaqi Bai, Tongliang Li, Zhoujun Li. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

The integration of multimodal Electronic Health Records (EHR) data has significantly advanced clinical predictive capabilities. Existing models, which utilize clinical notes and multivariate time-series EHR data, often fall short of incorporating the necessary medical context for accurate clinical tasks, while previous approaches with knowledge graphs (KGs) primarily focus on structured knowledge extraction. In response, we propose EMERGE, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR predictive modeling. We extract entities from both time-series data and clinical notes by prompting Large Language Models (LLMs) and align them with professional PrimeKG, ensuring consistency. In addition to triplet relationships, we incorporate entities' definitions and descriptions for richer semantics. The extracted knowledge is then used to generate task-relevant summaries of patients' health statuses. Finally, we fuse the summary with other modalities using an adaptive multimodal fusion network with cross-attention. Extensive experiments on the MIMIC-III and MIMIC-IV datasets' in-hospital mortality and 30-day readmission tasks demonstrate the superior performance of the EMERGE framework over baseline models. Comprehensive ablation studies and analysis highlight the efficacy of each designed module and robustness to data sparsity. EMERGE contributes to refining the utilization of multimodal EHR data in healthcare, bridging the gap with nuanced medical contexts essential for informed clinical predictions. We have publicly released the code at https://github.com/yhzhu99/EMERGE.

Multilingual translation supports multiple translation directions by projecting all languages in a shared space, but the translation quality is undermined by the difference between languages in the text-only modality, especially when the number of languages is large. To bridge this gap, we introduce visual context as the universal language-independent representation to facilitate multilingual translation. In this paper, we propose a framework to leverage the multimodal prompt to guide the Multimodal Multilingual Neural Machine Translation (m3P), which aligns the representations of different languages with the same meaning and generates the conditional vision-language memory for translation. We construct a multilingual multimodal instruction dataset (InstrMulti102) to support 102 languages Our method aims to minimize the representation distance of different languages by regarding the image as a central language. Experimental results show that m3P outperforms previous text-only baselines and multilingual multimodal methods by a large margin. Furthermore, the probing experiments validate the effectiveness of our method in enhancing translation under the low-resource and massively multilingual scenario.

New Intent Discovery (NID) aims to recognize known and infer new intent categories with the help of limited labeled and large-scale unlabeled data. The task is addressed as a feature-clustering problem and recent studies augment instance representation. However, existing methods fail to capture cluster-friendly representations, since they show less capability to effectively control and coordinate within-cluster and between-cluster distances. Tailored to the NID problem, we propose a Robust and Adaptive Prototypical learning (RAP) framework for globally distinct decision boundaries for both known and new intent categories. Specifically, a robust prototypical attracting learning (RPAL) method is designed to compel instances to gravitate toward their corresponding prototype, achieving greater within-cluster compactness. To attain larger between-cluster separation, another adaptive prototypical dispersing learning (APDL) method is devised to maximize the between-cluster distance from the prototype-to-prototype perspective. Experimental results evaluated on three challenging benchmarks (CLINC, BANKING, and StackOverflow) of our method with better cluster-friendly representation demonstrate that RAP brings in substantial improvements over the current state-of-the-art methods (even large language model) by a large margin (average 5.5% improvement).

With the rapid advancement of IT operations, managing and analyzing large data volumes efficiently for practical applications has become increasingly critical. Natural Language Processing (NLP) techniques have demonstrated remarkable capabilities in various tasks, including named entity recognition, machine translation, and dialogue systems. Recently, Large Language Models (LLMs) have achieved significant improvements across various domain-specific areas. However, there is a noticeable gap in the development of specialized Large Language Models (LLMs) tailored for IT operations. In this paper, we introduce the OWL, a large language model trained on our constructed Owl-Instruct with a wide range of IT-related information. Specifically, limited by the maximum input length, we propose the \textbf{H}omogeneous \textbf{M}arkov \textbf{C}ontext \textbf{E}xtension method (HMCE). The mixture-of-adapter strategy is leveraged to improve the parameter-efficient tuning across different domains or tasks. Further, we evaluate the performance of OWL on the Owl-Bench established by us and open IT-related benchmarks. OWL demonstrates superior performance results on IT tasks, which outperforms existing models by significant margins. Moreover, we hope that the findings of our work will provide more insights to revolutionize the techniques of IT operations with specialized LLMs.

Most previous sequential labeling models are task-specific, while recent years have witnessed the rise of generative models due to the advantage of unifying all named entity recognition (NER) tasks into the encoder-decoder framework. Although achieving promising performance, our pilot studies demonstrate that existing generative models are ineffective at detecting entity boundaries and estimating entity types. In this paper, we propose a multi-task Transformer, which incorporates an entity boundary detection task into the named entity recognition task. More concretely, we achieve entity boundary detection by classifying the relations between tokens within the sentence. To improve the accuracy of entity-type mapping during decoding, we adopt an external knowledge base to calculate the prior entity-type distributions and then incorporate the information into the model via the self- and cross-attention mechanisms. We perform experiments on extensive NER benchmarks, including flat, nested, and discontinuous NER datasets involving long entities. It substantially increases nearly$+0.3 \sim +1.5\;{F_1}$scores across a broad spectrum or performs closely to the best generative NER model. Experimental results show that our approach improves the performance of the generative NER model considerably.

Social network alignment, aiming at linking identical identities across different social platforms, is a fundamental task in social graph mining. Most existing approaches are supervised models and require a large number of manually labeled data, which are infeasible in practice considering the yawning gap between social platforms. Recently, isomorphism across social networks is incorporated as complementary to link identities from the distribution level, which contributes to alleviating the dependency on sample-level annotations. Adversarial learning is adopted to learn a shared projection function by minimizing the distance between two social distributions. However, the hypothesis of isomorphism might not always hold true as social user behaviors are generally unpredictable, and thus a shared projection function is insufficient to handle the sophisticated cross-platform correlations. In addition, adversarial learning suffers from training instability and uncertainty, which may hinder model performance. In this article, we propose a novel meta-learning-based social network alignment model Meta-SNA to effectively capture the isomorphism and the unique characteristics of each identity. Our motivation lies in learning a shared meta-model to preserve the global cross-platform knowledge and an adaptor to learn a specific projection function for each identity. Sinkhorn distance is further introduced as the distribution closeness measurement to tackle the limitations of adversarial learning, which owns an explicitly optimal solution and can be efficiently computed by the matrix scaling algorithm. Empirically, we evaluate the proposed model over multiple datasets, and the experimental results demonstrate the superiority of Meta-SNA.

Text recognition is a long-standing research problem for document digitalization. Existing approaches are usually built based on CNN for image understanding and RNN for char-level text generation. In addition, another language model is usually needed to improve the overall accuracy as a post-processing step. In this paper, we propose an end-to-end text recognition approach with pre-trained image Transformer and text Transformer models, namely TrOCR, which leverages the Transformer architecture for both image understanding and wordpiece-level text generation. The TrOCR model is simple but effective, and can be pre-trained with large-scale synthetic data and fine-tuned with human-labeled datasets. Experiments show that the TrOCR model outperforms the current state-of-the-art models on the printed, handwritten and scene text recognition tasks. The TrOCR models and code are publicly available at https://aka.ms/trocr.

Quantitative information plays an important part in the financial and data analysis areas. Prior work relied on pattern-matching methods and complex hand-crafted rules to extract quantitative information due to the lack of labeled data. Such methods can be unstable and difficult to scale to the open domain. In this paper, we study quantitative information extraction in the low-resource setting. We propose a search-based approach by searching from the syntactic structures to acquire basic training data. The search process is simple yet effective. Then, a prefix-based text-to-text generation method is employed to extract the quantitative information. The prefix design can fully leverage pre-trained language models for text generation to serve the information extraction purpose. Experimental results show that our approaches achieves high performance with a limited amount of labeled data. The extraction result could further boost the performance of other tasks such as quantitative reasoning.

Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.

Dialogue summarization aims to condense a given dialogue into a simple and focused summary text.Typically, both the roles' viewpoints and conversational topics change in the dialogue stream.Thus how to effectively handle the shifting topics and select the most salient utterance becomes one of the major challenges of this task.In this paper, we propose a novel topic-aware Global-Local Centrality (GLC) model to help select the salient context from all sub-topics.The centralities are constructed at both the global and local levels.The global one aims to identify vital sub-topics in the dialogue and the local one aims to select the most important context in each sub-topic.Specifically, the GLC collects sub-topic based on the utterance representations.And each utterance is aligned with one sub-topic.Based on the sub-topics, the GLC calculates globaland local-level centralities.Finally, we combine the two to guide the model to capture both salient context and sub-topics when generating summaries.Experimental results show that our model outperforms strong baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.Further analysis demonstrates that our GLC can exactly identify vital contents from sub-topics. 1

Named entity recognition (NER) is an important research problem in natural language processing. There are three types of NER tasks, including flat, nested and discontinuous entity recognition. Most previous sequential labeling models are task-specific, while recent years have witnessed the rising of generative models due to the advantage of unifying all NER tasks into the seq2seq model framework. Although achieving promising performance, our pilot studies demonstrate that existing generative models are ineffective at detecting entity boundaries and estimating entity types. This paper proposes a multi-task Transformer, which incorporates an entity boundary detection task into the named entity recognition task. More concretely, we achieve entity boundary detection by classifying the relations between tokens within the sentence. To improve the accuracy of entity-type mapping during decoding, we adopt an external knowledge base to calculate the prior entity-type distributions and then incorporate the information into the model via the self and cross-attention mechanisms. We perform experiments on an extensive set of NER benchmarks, including two flat, three nested, and three discontinuous NER datasets. Experimental results show that our approach considerably improves the generative NER model’s performance.

Out-of-Domain (OOD) detection from user utterances plays an important part in task-oriented dialogue systems. Recent studies utilize supervised or self-supervised contrastive learning (CL) to learn discriminative semantic features for OOD detection. The supervised contrastive learning (SCL) methods only model class-level features of different in-domain (IND) intents while self-supervised CL (SSCL) methods can model instance-level features. However, the SSCL methods require complex data augmentation and are vulnerable to intrinsic false-negative pairs. To address the issues above and leverage both types of CL, we propose a novel Label-Guided Contrastive Learning (LGCL) framework. LGCL models both instance-level and class-level discriminative semantic representations by employing the sample and its corresponding label simultaneously, such that the prior knowledge of IND can be fully leveraged. Experiment and analysis results on two public benchmark datasets show that the proposed method significantly outperforms baselines on the OOD detection task.

Natural language video localization (NLVL) aims to locate the matching span relevant to a given query sentence from an untrimmed video. This task requires not only understanding video and text but also aligning the semantics between video and language. Existing methods obtain vision-language representations via separate encoders, cross-modal interactions are not fine-grained enough, and the semantics are not fully aligned. In this paper, we address the vision-language alignment via joint modeling and contrastive learning. We propose a unified Video-Language Representation Network (UniNet), employing a transformer encoder to learn vision-language representations aligned. Simultaneously taking video and text as input, the encoder jointly learns the representations of both and captures the inter-relations between video and text. Then the representations are used by the predictor to locate the grounding video span. Besides, we train our model with contrastive learning to enhance vision-language representations in the training stage. Experiments on three benchmark datasets show that UniNet outperforms the baseline methods and adopting unified representation and contrastive learning can improve vision-language semantic alignment.

Commit messages concisely describe code changes in natural language and are important for program comprehension and maintenance. Previous studies proposed some approaches for automatic commit message generation, but their performance is limited due to inappropriate representation of code changes and improper combination of translation-based and retrieval-based approaches. To address these problems, this paper introduces a novel framework named COME, in which modification embeddings are used to represent code changes in a fine-grained way, a self-supervised generative task is designed to learn contextualized code change representation, and retrieval-based and translation-based methods are combined through a decision algorithm. The average improvement of COME over the state-of-the-art approaches is 9.2% on automatic evaluation metrics and 8.0% on human evaluation metrics. We also analyse the effectiveness of COME's three main components and each of them results in an improvement of 8.6%, 8.7% and 5.2%.

Commit message generation (CMG) is a challenging task in automated software engineering that aims to generate natural language descriptions of code changes for commits. Previous methods all start from the modified code snippets, outputting commit messages through template-based, retrieval-based, or learning-based models. While these methods can summarize what is modified from the perspective of code, they struggle to provide reasons for the commit. The correlation between commits and issues that could be a critical factor for generating rational commit messages is still unexplored. In this work, we delve into the correlation between commits and issues from the perspective of dataset and methodology. We construct the first dataset anchored on combining correlated commits and issues. The dataset consists of an unlabeled commit-issue parallel part and a labeled part in which each example is provided with human-annotated rational information in the issue. Furthermore, we propose ExGroFi (Extraction, Grounding, Ene-tuning), a novel paradigm that can introduce the correlation between commits and issues into the training phase of models. To evaluate whether it is effective, we perform comprehensive experiments with various state-of-the-art CMG models. The results show that compared with the original models, the performance of ExGroFi-enhanced models is significantly improved.

Knowledge-grounded conversation has led to great progress in producing informative dialog responses by leveraging external knowledge. This work focuses on two affiliated knowledge grounded conversation tasks:Knowledge SelectionandResponse Generation. Previous work followed the paradigm of selecting the most optimal knowledge piece to guide the conversation towards generating the proper response. However, some knowledge pieces, which are not recognized as optimal, may still benefit response generation. How to effectively leverage these relevant knowledge pieces for response generation still remain a tricky issue. To address this problem, we proposeKINet, aKnowledgeIncorporationNetwork, which deals with the problem by boosting both the knowledge selection and the response generation. The proposed model contains a negative enhanced knowledge approximator which improves knowledge selection by enhancing the dense representation of knowledge pieces, and a curriculum knowledge sampler which improves generated responses by incorporating more relevant knowledge pieces in an easy-to-hard manner. We conduct the experiment on two datasets of knowledge-grounded conversations, the results show that the proposed model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations.

Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose theGroup-Transformer model (GTrans) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. To corroborate the effectiveness of the proposed method, extensive experiments and analytic experiments are conducted on three bilingual translation benchmarks and three multilingual translation tasks, including the IWLST-14, IWLST-17, LDC, WMT-14, WMT-21 and OPUS-100 benchmark. Experimental and analytical results demonstrate that our model outperforms its Transformer counterparts by a consistent gain. Furthermore, it can be successfully scaled up to 60 encoder layers and 36 decoder layers.

The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications.Previous studies along this line primarily focused on perturbations in the natural language question side, neglecting the variability of tables.Motivated by this, we propose the Adversarial Table Perturbation (ATP) as a new attacking paradigm to measure the robustness of Textto-SQL models.Following this proposition, we curate ADVETA, the first robustness evaluation benchmark featuring natural and realistic ATPs.All tested state-of-the-art models experience dramatic performance drops on ADVETA, revealing models' vulnerability in real-world practices.To defend against ATP, we build a systematic adversarial training example generation framework tailored for better contextualization of tabular data.Experiments show that our approach not only brings the best robustness improvement against tableside perturbations but also substantially empowers models against NL-side perturbations.We release our benchmark and code at: https://github.com/microsoft/ContextualSP.

Unsupervised summarization methods have achieved remarkable results by incorporating representations from pre-trained language models. However, existing methods fail to consider efficiency and effectiveness at the same time when the input document is extremely long. To tackle this problem, in this paper, we proposed an efficient Coarse-to-Fine Facet-Aware Ranking (C2F-FAR) framework for unsupervised long document summarization, which is based on the semantic block. The semantic block refers to continuous sentences in the document that describe the same facet. Specifically, we address this problem by converting the one-step ranking method into the hierarchical multi-granularity two-stage ranking. In the coarse-level stage, we proposed a new segment algorithm to split the document into facet-aware semantic blocks and then filter insignificant blocks. In the fine-level stage, we select salient sentences in each block and then extract the final summary from selected sentences. We evaluate our framework on four long document summarization datasets: Gov-Report, BillSum, arXiv, and PubMed. Our C2F-FAR can achieve new state-of-the-art unsupervised summarization results on Gov-Report and BillSum. In addition, our method speeds up 4-28 times more than previous methods.

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to alleviate this problem. Existing methods for adversarial example generation (AEG) are word-level or character-level, which ignore the ubiquitous phrase structure. In this paper, we propose a Phrase-level Adversarial Example Generation (PAEG) framework to enhance the robustness of the translation model. Our method further improves the gradient-based word-level AEG method by adopting a phrase-level substitution strategy. We verify our method on three benchmarks, including LDC Chinese-English, IWSLT14 German-English, and WMT14 English-German tasks. Experimental results demonstrate that our approach significantly improves translation performance and robustness to noise compared to previous strong baselines.

Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features, which has attracted considerable attention from both natural language processing and computer vision communities.Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases in the real world.In other words, the multilingual multimodal machine translation (Multilingual MMT) task has not been investigated, which aims to handle the aforementioned issues by providing a shared semantic space for multiple languages.Besides, the image modality has no language boundaries, which is superior to bridging the semantic gap between languages.To this end, we first propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.Then, an effective baseline LVP-M 3 using visual prompts is proposed to support translations between different languages, which includes three stages (token encoding, language-aware visual prompt generation, and language translation).Extensive experimental results on our constructed benchmark datasets demonstrate the effectiveness of LVP-M 3 method for Multilingual MMT.* First two authors contributed equally.

A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs).However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model.We think the gap between pretraining and downstream tasks hinders the training of these redundant parameters, and results in a suboptimal performance of the overall model.In this paper, we present PATS (Perturbation According To Sensitivity), a noisy training mechanism which considers each parameter's importance in the downstream task to help fine-tune PLMs.The main idea of PATS is to add bigger noise to parameters with lower sensitivity and vice versa, in order to activate more parameters' contributions to downstream tasks without affecting the sensitive ones much.Extensive experiments conducted on different tasks of the GLUE benchmark show PATS can consistently empower the fine-tuning of different sizes of PLMs, and the parameters in the well-performing models always have more concentrated distributions of sensitivities, which experimentally proves the effectiveness of our method.

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless, multilingual training is plagued by language interference degeneration in shared parameters because of the negative interference among different translation directions, especially on high-resource languages. In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference, which adopts the two-stage training with the language-specific selection mechanism. Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder to enhance the translation quality of high-resource directions. Next, the model is further trained on all available corpora to transfer knowledge from high-resource languages (HRLs) to low-resource languages (LRLs). Experimental results show that HLT-MT outperforms various strong baselines on WMT-10 and OPUS-100 benchmarks. Furthermore, the analytic experiments validate the effectiveness of our method in mitigating the negative interference in multilingual training.

Most translation tasks among languages belong to the zero-resource translation problem where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) enables one-pass translation using shared semantic space for all languages compared to the two-pass pivot translation but often underperforms the pivot-based method. In this paper, we propose a novel method, named as Unified Multilingual Multiple teacher-student Model for NMT (UM4). Our method unifies source-teacher, target-teacher, and pivot-teacher models to guide the student model for the zero-resource translation. The source teacher and target teacher force the student to learn the direct source-target translation by the distilled knowledge on both source and target sides. The monolingual corpus is further leveraged by the pivot-teacher model to enhance the student model. Experimental results demonstrate that our model of 72 directions significantly outperforms previous methods on the WMT benchmark.

Relation extraction is a key task in Natural Language Processing (NLP), which aims to extract relations between entity pairs from given texts.Recently, relation extraction (RE) has achieved remarkable progress with the development of deep neural networks.Most existing research focuses on constructing explicit structured features using external knowledge such as knowledge graph and dependency tree.In this paper, we propose a novel method to extract multi-granularity features based solely on the original input sentences.We show that effective structured features can be attained even without external knowledge.Three kinds of features based on the input sentences are fully exploited, which are in entity mention level, segment level, and sentence level.All the three are jointly and hierarchically modeled.We evaluate our method on three public benchmarks: SemEval 2010 Task 8, Tacred, and Tacred Revisited.To verify the effectiveness, we apply our method to different encoders such as LSTM and BERT.Experimental results show that our method significantly outperforms existing state-of-the-art models that even use external knowledge.Extensive analyses demonstrate that the performance of our model is contributed by the capture of multi-granularity features and the model of their hierarchical structure.

The cold-start problem has been a long-standing issue in recommendation. Embedding-based recommendation models provide recommendations by learning embeddings for each user and item from historical interactions. Therefore, such embedding-based models perform badly for cold items which haven't emerged in the training set. The most common solutions are to generate the cold embedding for the cold item from its content features. However, the cold embeddings generated from contents have different distribution as the warm embeddings are learned from historical interactions. In this case, current cold-start methods are facing an interesting seesaw phenomenon, which improves the recommendation of either the cold items or the warm items but hurts the opposite ones. To this end, we propose a general framework named Generative Adversarial Recommendation (GAR). By training the generator and the recommender adversarially, the generated cold item embeddings can have similar distribution as the warm embeddings that can even fool the recommender. Simultaneously, the recommender is fine-tuned to correctly rank the "fake'' warm embeddings and the real warm embeddings. Consequently, the recommendation of the warms and the colds will not influence each other, thus avoiding the seesaw phenomenon. Additionally, GAR could be applied to any off-the-shelf recommendation model. Experiments on two datasets present that GAR has strong overall recommendation performance in cold-starting both the CF-based model (improved by over 30.18%) and the GNN-based model (improved by over 17.78%).

Recently Command and Control (C&C) servers have attracted considerable attention in botnets and domain generation algorithms (DGAs) further enhance the stealth of C&C servers. However, Algorithmically Generated Domains (AGDs) generated by DGAs can be easily detected by previous DGA detection approaches. More specifically, the previous DGAs are hard to satisfy domain name rules, low repetition rate, and anti-detection in practical scenarios simultaneously. Designing an outstanding DGA has become a crucial issue from the botnet owner’s perspective. To mitigate these problems, we propose Cdga, a Controllable DGA via Generative Adversarial Networks (GAN), which is a popular backbone model for text generation in the natural language processing (NLP) community.Controllable text generation approaches are adopted by Cdga to ensure no repetition in the generated domain names and compliance with the domain rules. In addition to cheating DGA detectors, GANs are exploited to equip Cdga with a powerful anti-detection ability. Furthermore, our proposed method uses the technique of NLP to force the AGDs to meet language rules, where the generated domain names are difficult for recognition by human. By utilizing the time-dependent seed, Cdga can dynamically generate domain names, ensuring that the malware can connect to the C&C server conditioned on a specific time stamp. Experimental results demonstrate that the domain names generated by our method are realistic enough to be resistant to the state-of-the-art DGA detectors.

Deep learning techniques based on the neural network have made significant achievements in various fields of artificial intelligence. However, model training requires large-scale data sets, these data sets are crowd-sourced and model parameters will contain the encoding of private information, resulting in the risk of privacy leakage. With the trend toward sharing pretrained models, the risk of stealing training data sets through member inference attacks and model inversion attacks is further heightened. To tackle the privacy-preserving problems in deep learning tasks, we propose an improved Differential Privacy Stochastic Gradient Descent algorithm, using Simulated Annealing algorithm and Laplace Smooth denoising mechanism to optimize the allocation method of privacy loss, replacing the constant clipping method with adaptive gradient clipping method to improve model accuracy. we also analyze privacy cost under random shuffle data batch processing method in detail within the framework of Subsampled Rényi Differential Privacy. Compared with the existing privacy protection training methods with fixed parameters and dynamic privacy parameters in classification tasks, our implementation and experiments show that we can use less privacy budget train deep neural networks with the nonconvex objective function, obtain a higher model evaluation, and have almost zero additional cost in terms of model complexity, training efficiency, and model quality.

Unsupervised extractive summarization aims to extract salient sentences from documents without labeled corpus. Existing methods are mostly graph-based by computing sentence centrality. These methods have two main problems: facet bias and redundant problems. Facet bias problem leads summarization models tend to select sentences within the same facet, which often leads to the ignoring of other vital facets, especially on long-document and multi-documents. First, to address the facet bias problem, we proposed a novel Facet-Aware centrality-based Ranking model (FAR). We let the model pay more attention to different facets by introducing a sentence-document weight. The weight is added to the sentence centrality score. FAR can alleviate redundancy to some extent. Then, to further reduce redundancy, we proposed a novel Redundancy- and Facet-Aware Ranking model (RFAR) which jointly models facet and redundancy by incorporating Determinantal Point Process (DPP) into the previous proposed FAR. We evaluate our FAR and RFAR on a wide range of summarization tasks that include 8 representative benchmark datasets. Experimental results show that FAR and RFAR consistently outperforms strong baselines, especially in long- and multi-document scenarios, and even perform comparably to some supervised models. Besides, we find that our methods can alleviate the position bias problem.

Visual question answering (VQA) has gained increasing attention in both natural language processing and computer vision. The attention mechanism plays a crucial role in relating the question to meaningful image regions for answer inference. However, most existing VQA methods: 1) learn the attention distribution either from free-form regions or detection boxes in the image, which is intractable in answering questions about the foreground object and background form, respectively and 2) neglect the prior knowledge of human attention and learn the attention distribution with an unguided strategy. To fully exploit the advantages of attention, the learned attention distribution should focus more on the question-related image regions, such as human attention for both the questions, about the foreground object and background form. To achieve this, this article proposes a novel VQA model, called adversarial learning of supervised attentions (ALSAs). Specifically, two supervised attention modules: 1) free form-based and 2) detection-based, are designed to exploit the prior knowledge for attention distribution learning. To effectively learn the correlations between the question and image from different views, that is, free-form regions and detection boxes, an adversarial learning mechanism is implemented as an interplay between two supervised attention modules. The adversarial learning reinforces the two attention modules mutually to make the learned multiview features more effective for answer inference. The experiments performed on three commonly used VQA datasets confirm the favorable performance of ALSA.

These days, social media users tend to express their feelings through sharing images online. Capturing the emotions embedded in these social images involves great research challenges and practical values. Most existing works concentrate on extracting the visual feature from a global view, while ignoring the fact that visual objects are also rich in emotion. How to leverage the multilevel visual features to improve the sentiment analysis performance is important yet challenging. Besides, existing works view each social image as an independent sample while ignoring the rich correlations among social images, which may be helpful in detecting visual emotion. In this article, we propose a novel model called social relations-guided multiattention networks (SRGMANs) to incorporate both the multilevel (region-level and object-level) visual features of a single image and the correlations among multiple social images to conduct visual sentiment analysis. Specifically, we first construct a heterogeneous network consisting of various types of social relations and introduce a heterogeneous network embedding method to learn the network representation for each image. Then, two visual attention branches (region attention network and object attention network) are devised to extract emotional and discriminative visual features. For each branch, we design a self-attention module to capture the emotional dependencies among visual parts. Besides, a network-guided attention module is also designed in each branch to focus on more network-related emotional visual parts with the guidance of the topology information. Finally, the attended visual features from the two attention models, together with network representation features, are combined within a holistic framework to predict the sentiment of social images. Extensive experiments demonstrate the superiority of our model on three benchmark datasets.

Due to the rich spatio-temporal visual content and complex multimodal relations, Video Question Answering (VideoQA) has become a challenging task and attracted increasing attention. Current methods usually leverage visual attention, linguistic attention, or self-attention to uncover latent correlations between video content and question semantics. Although these methods exploit interactive information between different modalities to improve comprehension ability, inter- and intra-modality correlations cannot be effectively integrated in a uniform model. To address this problem, we propose a novel VideoQA model called Cross-Attentional Spatio-Temporal Semantic Graph Networks (CASSG). Specifically, a multi-head multi-hop attention module with diversity and progressivity is first proposed to explore fine-grained interactions between different modalities in a crossing manner. Then, heterogeneous graphs are constructed from the cross-attended video frames, clips, and question words, in which the multi-stream spatio-temporal semantic graphs are designed to synchronously reasoning inter- and intra-modality correlations. Last, the global and local information fusion method is proposed to coalesce the local reasoning vector learned from multi-stream spatio-temporal semantic graphs and the global vector learned from another branch to infer the answer. Experimental results on three public VideoQA datasets confirm the effectiveness and superiority of our model compared with state-of-the-art methods.

Knowledge-driven dialog has shown remarkable performance to alleviate the problem of generating uninformative responses in the dialog system. However, incorporating knowledge coherently and accurately into response generation is still far from being solved. Previous works dropped into the paradigm of non-goal-oriented knowledge-driven dialog, they are prone to ignore the effect of dialog goal, which has potential impacts on knowledge exploitation and response generation. To address this problem, this paper proposes a Goal-Oriented Knowledge Copy network, GOKC. Specifically, a goal-oriented knowledge discernment mechanism is designed to help the model discern the knowledge facts that are highly correlated to the dialog goal and the dialog context. Besides, a context manager is devised to copy facts not only from the discerned knowledge but also from the dialog goal and the dialog context, which allows the model to accurately restate the facts in the generated response. The empirical studies are conducted on two benchmarks of goal-oriented knowledge-driven dialog generation. The results show that our model can significantly outperform several state-of-the-art models in terms of both automatic evaluation and human judgments.

We consider grounding open domain dialogues with images. Existing work assumes that both an image and a textual context are available, but image-grounded dialogues by nature are more difficult to obtain than textual dialogues. Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques. The likelihood of the two types of dialogues is then formulated by a response generator and an image reconstructor that are learned within a conditional variational auto-encoding framework. Empirical studies are conducted in both image-grounded conversation and text-based conversation. In the first scenario, image-grounded dialogues, especially under a low-resource setting, can be effectively augmented by textual dialogues with latent images; while in the second scenario, latent images can enrich the content of responses and at the same time keep them relevant to contexts.

Joint extraction of entities and relations focuses on detecting entity pairs and their relations simultaneously with a unified model. Based on the extraction order, previous works mainly solve this task through relation-last, relation-first and relation-middle manner. However, these methods still suffer from the template-dependency, non-entity detection and non-predefined relation prediction problem. To overcome these challenges, in this paper, we propose a unified multi-task learning framework to divide the task into three interacted sub-tasks. Specifically, we first introduce the type-attentional method for subject extraction to provide prior type information explicitly. Then, the subject-aware relation prediction is presented to select useful relations based on the combination of global and local semantics. Third, we propose a question generation based QA method for object extraction to obtain diverse queries automatically. Notably, our method detects subjects or objects without relying on NER models and thus it is capable of dealing with the non-entity scenario. Finally, three sub-tasks are integrated into a unified model through parameter sharing. Extensive experiments demonstrate that the proposed framework outperforms all the baseline methods on two benchmark datasets, and further achieve excellent performance for non-predefined relations.

Bo Zhang, Xiaoming Zhang, Yun Liu, Lei Cheng, Zhoujun Li. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

We propose a novel task of jointly repairing program codes and generating commit messages.Code repair and commit message generation are two essential and related tasks for software development.However, existing work usually performs the two tasks independently.We construct a multilingual triple dataset including buggy code, fixed code, and commit messages for this novel task.We provide the cascaded models as baseline, which are enhanced with different training approaches, including the teacher-student method, the multi-task method, and the backtranslation method.To deal with the error propagation problem of the cascaded method, the joint model is proposed that can both repair the code and generate the commit message in a unified framework.Experimental results show that the enhanced cascaded model with teacher-student method and multitask-learning method achieves the best score on different metrics of automated code repair, and the joint model behaves better than the cascaded model on commit message generation.

Embedding based methods are widely used for unsupervised keyphrase extraction (UKE) tasks.Generally, these methods simply calculate similarities between phrase embeddings and document embedding, which is insufficient to capture different context for a more effective UKE model.In this paper, we propose a novel method for UKE, where local and global contexts are jointly modeled.From a global view, we calculate the similarity between a certain phrase and the whole document in the vector space as transitional embedding based models do.In terms of the local view, we first build a graph structure based on the document where phrases are regarded as vertices and the edges are similarities between vertices.Then, we proposed a new centrality computation method to capture local salient information based on the graph structure.Finally, we further combine the modeling of global and local context for ranking.We evaluate our models on three public benchmarks (Inspec, DUC 2001, SemEval 2010) and compare with existing state-of-the-art models.The results show that our model outperforms most models while generalizing better on input documents with different domains and length.Additional ablation study shows that both the local and global information is crucial for unsupervised keyphrase extraction tasks.

Graph Convolutional Networks (GCNs) are powerful models for node representation learning tasks. However, the node representation in existing GCN models is usually generated by performing recursive neighborhood aggregation across multiple graph convolutional layers with certain sampling methods, which may lead to redundant feature mixing, needless information loss, and extensive computations. Therefore, in this paper, we propose a novel architecture named Non-Recursive Graph Convolutional Network (NRGCN) to improve both the training efficiency and the learning performance of GCNs in the context of node classification. Specifically, NRGCN proposes to represent different hops of neighbors for each node based on inner-layer aggregation and layer-independent sampling. In this way, each node can be directly represented by concatenating the information extracted independently from each hop of its neighbors thereby avoiding the recursive neighborhood expansion across layers. Moreover, the layer-independent sampling and aggregation can be precomputed before the model training, thus the training process can be accelerated considerably. Extensive experiments on benchmark datasets verify that our NRGCN outperforms the state-of-the-art GCN models, in terms of the node classification performance and reliability.

Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, Ming Zhou. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Modern search engines retrieve results mainly based on the keyword matching techniques, and thus fail to answer analytical queries like "apps with more than 1 billion monthly active users" or "population growth of the US from 2015 to 2019", which requires numerical reasoning or aggregating results from multiple web pages. Such analytical queries are very common in the data analysis area, the expected results would be structured tables or charts. In most cases, these structured results are not available or accessible, they scatter in various text sources. In this work, we build AnaSearch, a search system to support analytical queries, and return structured results that can be visualized in the form of tables or charts. We collect and build structured quantitative data from the unstructured text on the web automatically. With AnaSearch, data analysts could easily derive insights for decision making with keyword or natural language queries. Specifically, we build AnaSearch under the COVID-19 news data, which makes it easy to compare with manually collected structured data.

Learning the representation for social images has recently made remarkable achievements for many tasks, such as cross-modal retrieval and multilabel classification. However, since social images contain both multimodal contents (e.g., visual images and textual descriptions) and social relations among images, simply modeling the content information may lead to suboptimal embedding. In this paper, we propose a novel multimodal representation learning model for social images, that is, correlational multimodal variational autoencoder (CMVAE) via triplet network. Specifically, in order to mine the highly nonlinear correlation between the visual content and the textual content, a CMVAE is proposed to learn a unified representation for the multiple modalities of social images. Both common information in all modalities and private information in each modality are encoded for the representation learning. To incorporate the social relations among images, we employ the triplet network to embed multiple types of social links in the representation learning. Then, a joint embedding model is proposed to combine the social relations for representation learning of the multimodal contents. Comprehensive experiment results on four datasets confirm the effectiveness of our method in two tasks, namely, multilabel classification and cross-modal retrieval. Our method outperforms the state-of-the-art multimodal representation learning methods with significant improvement of performance.

Application repackaging is a severe threat to Android users and the market. Not only does it infringe on intellectual property, but it is also one of the most common ways of propagating mobile malware. Existing countermeasures mostly detect repackaging based on app similarity measurement, which tends to be imprecise when obfuscations are applied to repackaged apps. Moreover, they rely on a central party, typically the hosting app store, to perform the detection, but many app stores fail to commit proper effort to piracy detection. We consider building the application repackaging detection capability into apps, such that user devices are made use to detect repackaging in a decentralized fashion.The main challenge is how to protect the detection code from being manipulated by attacks. We propose a creative use oflogic bombs, which are otherwise regularly used in malware. Thetrigger conditionsof bombs are constructed to exploit the differences between the attacker and users, such that a bomb that lies dormant on the attacker side will be activated on the user side. The detection code, which is part of the bombpayload, is executed only if the bomb is activated. We introducecryptographically obfuscated logic bombto enhance the bomb: (1) the detection code iswoveninto the neighboring original app code, (2) the mixed code gets encrypted using a key, and (3) the key is deleted from the app and can only be derived when the bomb is activated. Thus, attacks that try to modify or delete the detection code will corrupt the app itself, and searching the key in the application will be in vain. Moreover, we propose abomb sprayingtechnique that allows many bombs to be injected into an app, multiplying the needed adversary effort for bypassing the detection. In addition to repackaging detection, we present application tampering detection to fight attacks that insert malicious code into repackaged apps. We have implemented a prototype, namedBombDroid, that builds repackaging and tampering detection into apps through bytecode instrumentation. The evaluation and the security analysis show that the technique is effective, efficient, and resilient to various bomb analysis techniques including fuzzing, symbolic execution, multi-path exploration, and program slicing. Ethical issues due to the use of logic bombs are also discussed.

In the circumstance of social big data, sentiment analysis is attracting increasing attention for its capacity in understanding individuals' attitudes and feelings. Traditional sentiment analysis methods focus on single modality and become ineffective as enormous data are emerging on the social websites with multiple manifestations. In this article, multimodal learning approaches are proposed to capture the relations between image and text, which only stay at the region level and ignore the fact that the channels are also closely correlated with the semantic information. In addition, social images in the social platforms are closely connected by various types of relations, which are also conducice to sentiment classification but neglected by most existing works. In this article, we propose an attention-based heterogeneous relational model to improve the multimodal sentiment analysis performance by incorporating rich social information. Specifically, we propose a progressive dual attention module to capture the correlations between image and text, and then learn the joint image-text representation from the perspective of content information. A channel attention schema is proposed here to highlight semantically rich image channels and a region attention schema is further designed to highlight the emotional regions based on the attended channels. After that, we construct a heterogeneous relation network and extend graph convolutional network to aggregate the content information from social contexts as complements to learn high-quality representations of social images. Our proposal is thoroughly evaluated on two benchmark datasets, and experimental results demonstrate the superiority of the proposed model.

Visual question answering (VQA) has been proposed as a challenging task and attracted extensive research attention. It aims to learn a joint representation of the question-image pair for answer inference. Most of the existing methods focus on exploring the multi-modal correlation between the question and image to learn the joint representation. However, the answer-related information is not fully captured by these methods, which results that the learned representation is ineffective to reflect the answer of the question. To tackle this problem, we propose a novel model, i.e., adversarial learning with multi-modal attention (ALMA), for VQA. An adversarial learning-based framework is proposed to learn the joint representation to effectively reflect the answer-related information. Specifically, multi-modal attention with the Siamese similarity learning method is designed to build two embedding generators, i.e., question-image embedding and question-answer embedding. Then, adversarial learning is conducted as an interplay between the two embedding generators and an embedding discriminator. The generators have the purpose of generating two modality-invariant representations for the question-image and question-answer pairs, whereas the embedding discriminator aims to discriminate the two representations. Both the multi-modal attention module and the adversarial networks are integrated into an end-to-end unified framework to infer the answer. Experiments performed on three benchmark data sets confirm the favorable performance of ALMA compared with state-of-the-art approaches.

Language model pre-training has achieved success in many natural language processing tasks. Existing methods for cross-lingual pre-training adopt Translation Language Model to predict masked words with the concatenation of the source sentence and its target equivalent. In this work, we introduce a novel cross-lingual pre-training method, called Alternating Language Modeling (ALM). It code-switches sentences of different languages rather than simple concatenation, hoping to capture the rich cross-lingual context of words and phrases. More specifically, we randomly substitute source phrases with target translations to create code-switched sentences. Then, we use these code-switched data to train ALM model to learn to predict words of different languages. We evaluate our pre-training ALM on the downstream tasks of machine translation and cross-lingual classification. Experiments show that ALM can outperform the previous pre-training methods on three benchmarks.1

Although neural machine translation (NMT) has achieved significant progress in recent years, most previous NMT models only depend on the source text to generate translation.Inspired by the success of template-based and syntax-based approaches in other fields, we propose to use extracted templates from tree structures as soft target templates to guide the translation procedure.In order to learn the syntactic structure of the target sentences, we adopt the constituency-based parse tree to generate candidate templates.We incorporate the template information into the encoder-decoder framework to jointly utilize the templates and source text.Experiments show that our model significantly outperforms the baseline models on four benchmarks and demonstrate the effectiveness of soft target templates.

The technique of recursive neighborhood aggregation has dominated the implementation of existing successful Graph Neural Networks (GNNs). However, the recursive information propagation across layers inevitably brings in extra calculations, potentially large variance, and difficulty of parallel computation. In this paper, we propose Graph Unfolding Networks (GUNets) as an alternative mechanism of recursive neighborhood aggregation for graph representation learning. Comparing to generic GNNs, our proposed GUNets are efficient, robust and practically effective. At their core, GUNets unfold the local structure of every node, i.e. the rooted tree, to a set of trajectories, and then adopt set function to capture the topology of the rooted subtree, which is more convenient for parallel computation than the recursive neighborhood aggregation process. More importantly, through a specific design of the set function, our architecture enables efficient and robust learning on large-scale graphs without resorting to any pruning of the rooted subtree that is usually necessary in generic GNNs. Extensive experiments on five large datasets (the number of nodes ranges from 104 to 106) show that our GUNets achieve comparable or even better results than current successful GNNs while gaining significantly more efficiency and lower accuracy variance. Codes can be found at github.com/GUNets/GUNets.

Recent advances in Graph Convolutional Networks (GCNs) have led to state-of-the-art performance on various graph-related tasks. However, most existing GCN models do not explicitly identify whether all the aggregated neighbors are valuable to the learning tasks, which may harm the learning performance. In this paper, we consider the problem of node classification and propose the Label-Aware Graph Convolutional Network (LAGCN) framework which can directly identify valuable neighbors to enhance the performance of existing GCN models. Our contribution is three-fold. First, we propose a label-aware edge classifier that can filter distracting neighbors and add valuable neighbors for each node to refine the original graph into a label-aware (LA) graph. Existing GCN models can directly learn from the LA graph to improve the performance without changing their model architectures. Second, we introduce the concept of positive ratio to evaluate the density of valuable neighbors in the LA graph. Theoretical analysis reveals that using the edge classifier to increase the positive ratio can improve the learning performance of existing GCN models. Third, we conduct extensive node classification experiments on benchmark datasets. The results verify that LAGCN can improve the performance of existing GCN models considerably, in terms of node classification.

Document layout analysis usually relies on computer vision models to understand documents while ignoring textual information that is vital to capture.Meanwhile, high quality labeled datasets with both visual and textual information are still insufficient.In this paper, we present DocBank, a benchmark dataset that contains 500K document pages with fine-grained tokenlevel annotations for document layout analysis.DocBank is constructed using a simple yet effective way with weak supervision from the L A T E X documents available on the arXiv.com.With DocBank, models from different modalities can be compared fairly and multi-modal approaches will be further investigated and boost the performance of document layout analysis.We build several strong baselines and manually split train/dev/test sets for evaluation.Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents.The DocBank dataset is publicly available at https: //github.com/doc-analysis/DocBank.

Conventional approaches for formality style transfer borrow models from neural machine translation, which typically requires massive parallel data for training. However, the dataset for formality style transfer is considerably smaller than translation corpora. Moreover, we observe that informal and formal sentences closely resemble each other, which is different from the translation task where two languages have different vocabularies and grammars. In this paper, we present a new approach, Sequence-to-Sequence with Shared Latent Space (S2S-SLS), for formality style transfer, where we propose two auxiliary losses and adopt joint training of bi-directional transfer and auto-encoding. Experimental results show that S2S-SLS (with either RNN or Transformer architectures) consistently outperforms baselines in various settings, especially when we have limited data.

Recent advances cast the entity-relation extraction to a multi-turn question answering (QA) task and provide an effective solution based on the machine reading comprehension (MRC) models. However, they use a single question to characterize the meaning of entities and relations, which is intuitively not enough because of the variety of context semantics. Meanwhile, existing models enumerate all relation types to generate questions, which is inefficient and easily leads to confusing questions. In this paper, we improve the existing MRC-based entity-relation extraction model through diverse question answering. First, a diversity question answering mechanism is introduced to detect entity spans and two answering selection strategies are designed to integrate different answers. Then, we propose to predict a subset of potential relations and filter out irrelevant ones to generate questions effectively. Finally, entity and relation extractions are integrated in an end-to-end way and optimized through joint learning. Experiment results show that the proposed method significantly outperforms baseline models, which improves the relation F1 to 62.1% (+1.9%) on ACE05 and 71.9% (+3.0%) on CoNLL04. Our implementation is available at https://github.com/TanyaZhao/MRC4ERE.

Text summarization plays an important role in various NLP applications. Using templates with generation methods is an effective way to address abstractive summarization. However, existing template-enhanced generation approaches use templates in a naive way and mainly adopt RNN-based Seq2Seq models, so they cannot make full use of valid information in the templates and suffer from templates' noise. To mitigate these problems, we propose a new abstractive summarization model called Summarization Transformer with Template-aware Representation (STTR), which uses a template-aware document encoding module and a document representation shifting loss to preserve the useful information and filter the noise of the template. The experiments on the Gigaword and LCSTS datasets show that our method outperforms baseline models and achieves a new state-of-the-art.

We present TableBank, a new image-based table detection and recognition dataset built with novel weak supervision from Word and Latex documents on the internet. Existing research for image-based table detection and recognition usually fine-tunes pre-trained models on out-of-domain data with a few thousand human-labeled examples, which is difficult to generalize on real-world applications. With TableBank that contains 417K high quality labeled tables, we build several strong baselines using state-of-the-art models with deep neural networks. We make TableBank publicly available and hope it will empower more deep learning approaches in the table detection and recognition task. The dataset and models can be downloaded from https://github.com/doc-analysis/TableBank.

Virtual try-on has attracted lots of research attention due to its potential applications in e-commerce, virtual reality and fashion design. However, existing methods can hardly preserve the fine-grained details (e.g., clothing texture, facial identity, hair style, skin tone) during generation, due to the non-rigid body deformation and multi-scale details. In this work, we propose a multi-stage framework to synthesize person images, where fine-grained details can be well preserved. To address the long-range translation and rich-details generation, we propose a Tree-Block (tree dilated fusion block) to replace standard ResNet-block where applicable. Notably, multi-scale feature maps can be smoothly fused for fine-grained detail generation, by incorporating larger spatial context at multiple scales. With a delicate end-to-end training scheme, our whole framework can be jointly optimized for results with significantly better visual fidelity and richer details. Moreover, we also explore the potential application in video-based virtual try-on. By harnessing the well-trained image generator and an extra video-level adaptor, a model photo can be well animated with a driving pose sequence. Extensive evaluations on standard datasets and user study demonstrate that our proposed framework achieves the state-of-the-art results, especially in preserving visual details in clothing texture and facial identity. Our implementation is publicly available via https://github.com/JDAI-CV/Down-to-the-Last-Detail-Virtual-Try-on-with-Detail-Carving.

Ransomware is a new business model for cybercrime which mainly targets individual users and machines. Many events have shown how profitable the technique can be. Industrial control systems (ICS) are becoming the next domain. More and more researchers and attackers have become the focus on this field and presented some ICS ransomware. But existing ICS ransomware is theoretically feasible and has a limited effect on real ICS. In this work, we present ICS-BROCK, a full-fledged ICS ransomware that can compromise a real-world. To demonstrate the capability of ICS-BROCK, we use SIEMENS S7-300 PLC, one of the most widely used devices in ICSs, to build a real water treatment environment. The results empirically demonstrate the feasibility of launching ICS ransomware attacks in a practical setting. In the end, we give some suggestions on ICS ransomware to aid in future study and defenses.

Sentiment analysis of social multimedia data has attracted extensive research interest and has been applied to many tasks, such as election prediction and products evaluation. Sentiment analysis of one modality (e.g., text or image) has been broadly studied. However, not much attention has been paid to the sentiment analysis of multimodal data. Different modalities usually have information that is complementary. Thus, it is necessary to learn the overall sentiment by combining the visual content with text description. In this article, we propose a novel method—Attention-Based Modality-Gated Networks (AMGN)—to exploit the correlation between the modalities of images and texts and extract the discriminative features for multimodal sentiment analysis. Specifically, a visual-semantic attention model is proposed to learn attended visual features for each word. To effectively combine the sentiment information on the two modalities of image and text, a modality-gated LSTM is proposed to learn the multimodal features by adaptively selecting the modality that presents stronger sentiment information. Then a semantic self-attention model is proposed to automatically focus on the discriminative features for sentiment classification. Extensive experiments have been conducted on both manually annotated and machine weakly labeled datasets. The results demonstrate the superiority of our approach through comparison with state-of-the-art models.

Open domain response generation has achieved remarkable progress in recent years, but sometimes yields short and uninformative responses. We propose a new paradigm, prototypethen-edit for response generation, that first retrieves a prototype response from a pre-defined index and then edits the prototype response according to the differences between the prototype context and current context. Our motivation is that the retrieved prototype provides a good start-point for generation because it is grammatical and informative, and the post-editing process further improves the relevance and coherence of the prototype. In practice, we design a contextaware editing model that is built upon an encoder-decoder framework augmented with an editing vector. We first generate an edit vector by considering lexical differences between a prototype context and current context. After that, the edit vector and the prototype response representation are fed to a decoder to generate a new response. Experiment results on a large scale dataset demonstrate that our new paradigm significantly increases the relevance, diversity and originality of generation results, compared to traditional generative models. Furthermore, our model outperforms retrieval-based methods in terms of relevance and originality.

Nowadays, it is common for one natural person to join multiple social networks to enjoy different kinds of services. Linking identical users across multiple social networks, also known as social network alignment, is an important problem of great research challenges. Existing methods usually link social identities on the pairwise sample level, which may lead to undesirable performance when the number of available annotations is limited. Motivated by the isomorphism information, in this paper we consider all the identities in a social network as a whole and perform social network alignment from the distribution level. The insight is that we aim to learn a projection function to not only minimize the distance between the distributions of user identities in two social networks, but also incorporate the available annotations as the learning guidance. We propose three models SNNAu, SNNAb and SNNAo to learn the projection function under the weakly-supervised adversarial learning framework. Empirically, we evaluate the proposed models over multiple datasets, and the results demonstrate the superiority of our proposals.

With the increasing popularity and diversity of social media, users tend to join multiple social platforms to enjoy different types of services. User identity linkage, which aims to link identical identities across different social platforms, has attracted increasing research attentions recently. Existing methods usually focus on pairwise identity linkage between two platforms, which cannot piece up the information from multi-sources to depict the intrinsic figures of social users. In this paper, we propose a novel adversarial learning based framework MSUIL with partially shared generators to perform Semi-supervised User Identity Linkage across Multiple social networks. The isomorphism across multiple platforms is captured as the complementary to link identities. The insight is that we aim to learn the desirable projection functions (generators) to not only minimize the distance between the distributions of user identities in arbitrary pairs of platforms, but also incorporate the available annotations as the learning guidance. The projection functions of different platform pairs share partial parameters, which ensures MSUIL can capture the interdependencies among multiple platforms and improves the model efficiency. Empirically, we evaluate our proposal over multiple datasets. The experimental results demonstrate the superiority of the proposed MSUIL model.

Network embedding, as a promising way of the network representation learning, is capable of supporting various subsequent network mining and analysis tasks, and has attracted growing research interests recently. Traditional approaches assign each node with an independent continuous vector, which will cause memory overhead for large networks. In this paper we propose a novel multi-hot compact network embedding framework to effectively reduce memory cost by learning partially shared embeddings. The insight is that a node embedding vector is composed of several basis vectors according to a multi-hot index vector. The basis vectors are shared by different nodes, which can significantly reduce the number of continuous vectors while maintain similar data representation ability. Specifically, we propose a MCNE$_p $ model to learn compact embeddings from pre-learned node features. A novel component named compressor is integrated into MCNE$_p $ to tackle the challenge that popular back-propagation optimization cannot propagate loss through discrete samples. We further propose an end-to-end model MCNE$_t $ to learn compact embeddings from the input network directly. Empirically, we evaluate the proposed models over four real network datasets, and the results demonstrate that our proposals can save about 90% of memory cost of network embeddings without significantly performance decline.

Haoyan Liu, Lei Fang, Qian Liu, Bei Chen, Jian-Guang Lou, Zhoujun Li. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Yunli Wang, Yu Wu, Lili Mou, Zhoujun Li, Wenhan Chao. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Ze Yang, Wei Wu, Jian Yang, Can Xu, Zhoujun Li. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Ze Yang, Can Xu, Wei Wu, Zhoujun Li. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Although browser extensions bring users a better experience, it creates a hidden danger of privacy leakage. A common privacy leakage detection method is realized through detecting private data transmission. However, only the unintended transmission is considered to be a privacy leak. Therefore, the real challenge is to determine whether or not the transmission is user intended. In order to address this problem, we check the rationality of private data transmission by establishing a privacy model based on classification for extensions to confirm the scope of private data that can be uploaded and domains that can be sent to. Furthermore, we present BEDS (Browser Extension Detection System), a Chromium based extension dynamic detection system. BEDS first builds a privacy model for each extension and then records the extension's network logs and browser API logs when accessing specified pages. Finally, BEDS determines whether there exists a privacy leak according to the strict privacy leakage judgment rules. We test our implementation in large scale on extensions in browsers developed by China's three major Internet companies and complete 15 months of continuous tracking. After examining a total of 14,487 extensions, 1,897 privacy leaks are identified, all results have been inspected by manual and the accuracy of BEDS is over 97%. A number of domains that illegally collect private user data are discovered and tracked. Our results show that about 47,000 Chinese IPs upload private information to suspicious servers every day.

We study the problem of response selection for multi-turn conversation in retrieval-based chatbots. The task involves matching a response candidate with a conversation context, the challenges for which include how to recognize important parts of the context, and how to model the relationships among utterances in the context. Existing matching methods may lose important information in contexts as we can interpret them with a unified framework in which contexts are transformed to fixed-length vectors without any interaction with responses before matching. This motivates us to propose a new matching framework that can sufficiently carry important information in contexts to matching and model relationships among utterances at the same time. The new framework, which we call a sequential matching framework (SMF), lets each utterance in a context interact with a response candidate at the first step and transforms the pair to a matching vector. The matching vectors are then accumulated following the order of the utterances in the context with a recurrent neural network (RNN) that models relationships among utterances. Context-response matching is then calculated with the hidden states of the RNN. Under SMF, we propose a sequential convolutional network and sequential attention network and conduct experiments on two public data sets to test their performance. Experiment results show that both models can significantly outperform state-of-the-art matching methods. We also show that the models are interpretable with visualizations that provide us insights on how they capture and leverage important information in contexts for matching.

Image-text matching by deep models has recently made remarkable achievements in many tasks, such as image caption and image search. A major challenge of matching the image and text lies in that they usually have complicated underlying relations between them and simply modeling the relations may lead to suboptimal performance. In this paper, we develop a novel approach Bi-directional Spatial-Semantic Attention Networks (BSSAN), which leverages both the word to regions (W2R) relation and image object to words (O2W) relation in a holistic deep framework for more effectively matching. Specifically, to effectively encode the W2R relation, we adopt LSTM with bilinear attention function to infer the image regions which are more related to the particular words, which is referred as the W2R attention network. On the other side, the O2W attention network is proposed to discover the semanticallyclose words for each visual object in the image, i.e., the visual object to words (O2W) relation. Then a deep model unifying both of the two directional attention networks into a holistic learning framework is proposed to learn the matching scores of image and text pairs. Compared to existing image-text matching methods, our approach achieves state-of-the-art performance on the datasets of Flickr30K and MSCOCO.

Long text brings a big challenge to neural network based text matching approaches due to their complicated structures. To tackle the challenge, we propose a knowledge enhanced hybrid neural network (KEHNN) that leverages prior knowledge to identify useful information and filter out noise in long text and performs matching from multiple perspectives. The model fuses prior knowledge into word representations by knowledge gates and establishes three matching channels with words, sequential structures of text given by Gated Recurrent Units (GRUs), and knowledge enhanced representations. The three channels are processed by a convolutional neural network to generate high level features for matching, and the features are synthesized as a matching score by a multilayer perceptron. In this paper, we focus on exploring the use of taxonomy knowledge for text matching. Evaluation results from extensive experiments on public data sets of question answering and conversation show that KEHNN can significantly outperform state-of-the-art matching models and particularly improve matching accuracy on pairs with long text.

We study response generation for open domain conversation in chatbots. Existing methods assume that words in responses are generated from an identical vocabulary regardless of their inputs, which not only makes them vulnerable to generic patterns and irrelevant noise, but also causes a high cost in decoding. We propose a dynamic vocabulary sequence-to-sequence (DVS2S) model which allows each input to possess their own vocabulary in decoding. In training, vocabulary construction and response generation are jointly learned by maximizing a lower bound of the true objective with a Monte Carlo sampling method. In inference, the model dynamically allocates a small vocabulary for an input with the word prediction model, and conducts decoding only with the small vocabulary. Because of the dynamic vocabulary mechanism, DVS2S eludes many generic patterns and irrelevant words in generation, and enjoys efficient decoding at the same time. Experimental results on both automatic metrics and human annotations show that DVS2S can significantly outperform state-of-the-art methods in terms of response quality, but only requires 60% decoding time compared to the most efficient baseline.

We present assertion based question answering (ABQA), an open domain question answering task that takes a question and a passage as inputs, and outputs a semi-structured assertion consisting of a subject, a predicate and a list of arguments. An assertion conveys more evidences than a short answer span in reading comprehension, and it is more concise than a tedious passage in passage-based QA. These advantages make ABQA more suitable for human-computer interaction scenarios such as voice-controlled speakers. Further progress towards improving ABQA requires richer supervised dataset and powerful models of text understanding. To remedy this, we introduce a new dataset called WebAssertions, which includes hand-annotated QA labels for 358,427 assertions in 55,960 web passages. To address ABQA, we develop both generative and extractive approaches. The backbone of our generative approach is sequence to sequence learning. In order to capture the structure of the output assertion, we introduce a hierarchical decoder that first generates the structure of the assertion and then generates the words of each field. The extractive approach is based on learning to rank. Features at different levels of granularity are designed to measure the semantic relevance between a question and an assertion. Experimental results show that our approaches have the ability to infer question-aware assertions from a passage. We further evaluate our approaches by incorporating the ABQA results as additional features in passage-based QA. Results on two datasets show that ABQA features significantly improve the accuracy on passage-based QA.

Application repackaging is a severe threat to Android users and the market. Existing countermeasures mostly detect repackaging based on app similarity measurement and rely on a central party to perform detection, which is unscalable and imprecise. We instead consider building the detection capability into apps, such that user devices are made use of to detect repackaging in a decentralized fashion. The main challenge is how to protect repackaging detection code from attacks. We propose a creative use of logic bombs, which are regularly used in malware, to conquer the challenge. A novel bomb structure is invented and used: the trigger conditions are constructed to exploit the differences between the attacker and users, such that a bomb that lies dormant on the attacker side will be activated on one of the user devices, while the repackaging detection code, which is packed as the bomb payload, is kept inactive until the trigger conditions are satisfied. Moreover, the repackaging detection code is woven into the original app code and gets encrypted; thus, attacks by modifying or deleting suspicious code will corrupt the app itself. We have implemented a prototype, named BombDroid, that builds the repackaging detection into apps through bytecode instrumentation, and the evaluation shows that the technique is effective, efficient, and resilient to various adversary analysis including symbol execution, multi-path exploration, and program slicing.

Nowadays, it is common for one natural person to join multiple social networks to enjoy different services. Linking identical users across different social networks, also known as the User Identity Linkage (UIL), is an important problem of great research challenges and practical value. Most existing UIL models are supervised or semi-supervised and a considerable number of manually matched user identity pairs are required, which is costly in terms of labor and time. In addition, existing methods generally rely heavily on some discriminative common user attributes, and thus are hard to be generalized. Motivated by the isomorphism across social networks, in this paper we consider all the users in a social network as a whole and perform UIL from the user space distribution level. The insight is that we convert the unsupervised UIL problem to the learning of a projection function to minimize the distance between the distributions of user identities in two social networks. We propose to use the earth mover's distance (EMD) as the measure of distribution closeness, and propose two models UUIL$_gan $ and UUIL$_omt $ to efficiently learn the distribution projection function. Empirically, we evaluate the proposed models over multiple social network datasets, and the results demonstrate that our proposal significantly outperforms state-of-the-art methods.

Visual Question Answering (VQA) aims to learn a joint embedding of the question sentence and the corresponding image to infer the answer. Existing approaches learn the joint embedding don't consider the answer-related information, which results in that the learned representation is not effective to reflect the answer of the question. To address this problem, this paper proposes a novel method, i.e., Adversarial Learning of Answer-Related Representation (ALARR) for visual question answering, which seeks an effective answer-related representation for the question-image pair based on adversarial learning between two processes. The embedding learning process aims to generate modality-invariant joint representations for the question-image and question-answer pairs, respectively. Meanwhile, it tries to confuse the other process, embedding discriminator, which tries to discriminate the two representations from different modalities of pairs. Specifically, the joint embedding of the question-image pair is learned by a three-level attention model, and the joint representation of the question-answer pair is learned by a semantic integration model. Through the adversarial leaning, the answer-related representation are better preserved. Then an answer predictor is proposed to infer the answer from the answer-related representation. Experiments conducted on two widely used VQA benchmark datasets demonstrate that the proposed model outperforms the state-of-the-art approaches.

In this paper, we study automatic keyphrase generation.Although conventional approaches to this task show promising results, they neglect correlation among keyphrases, resulting in duplication and coverage issues.To solve these problems, we propose a new sequence-to-sequence architecture for keyphrase generation named CorrRNN, which captures correlation among multiple keyphrases in two ways.First, we employ a coverage vector to indicate whether the word in the source document has been summarized by previous phrases to improve the coverage for keyphrases.Second, preceding phrases are taken into account to eliminate duplicate phrases and improve result coherence.Experiment results show that our model significantly outperforms the state-of-the-art method on benchmark datasets in terms of both accuracy and diversity.

The explosive use of social media makes it a popular platform for malicious users, known as social spammers, to overwhelm legitimate users with unwanted content. Most existing social spammer detection approaches are supervised and need a large number of manually labeled data for training, which is infeasible in practice. To address this issue, some semi-supervised models are proposed by incorporating side information such as user profiles and posted tweets. However, these shallow models are not effective to deeply learn the desirable user representations for spammer detection, and the multi-view data are usually loosely coupled without considering their correlations. In this paper, we propose a Semi-Supervised Deep social spammer detection model by Multi-View data fusion (SSDMV). The insight is that we aim to extensively learn the task-relevant discriminative representations for users to address the challenge of annotation scarcity. Under a unified semi-supervised learning framework, we first design a deep multi-view feature learning module which fuses information from different views, and then propose a label inference module to predict labels for users. The mutual refinement between the two modules ensures SSDMV to be able to both generate high quality features and make accurate predictions.Empirically, we evaluate SSDMV over two real social network datasets on three tasks, and the results demonstrate that SSDMV significantly outperforms the state-of-the-art methods.

Relation extraction has been widely studied to extract new relational facts from open corpus. Previous relation extraction methods are faced with the problem of wrong labels and noisy data, which substantially decrease the performance of the model. In this paper, we propose an ensemble neural network model - Adaptive Boosting LSTMs with Attention, to more effectively perform relation extraction. Specifically, our model first employs the recursive neural network LSTMs to embed each sentence. Then we import attention into LSTMs by considering that the words in a sentence do not contribute equally to the semantic meaning of the sentence. Next via adaptive boosting, we build strategically several such neural classifiers. By ensembling multiple such LSTM classifiers with adaptive boosting, we could build a more effective and robust joint ensemble neural networks based relation extractor. Experiment results on real dataset demonstrate the superior performance of the proposed model, improving F1-score by about 8% compared to the state-of-the-art models.

Learning the embedding for social media data has attracted extensive research interests as well as boomed a lot of applications, such as classification and link prediction. In this paper, we examine the scenario of a multimodal network with nodes containing multimodal contents and connected by heterogeneous relationships, such as social images containing multimodal contents (e.g., visual content and text description), and linked with various forms (e.g., in the same album or with the same tag). However, given the multimodal network, simply learning the embedding from the network structure or a subset of content results in sub-optimal representation. In this paper, we propose a novel deep embedding method, i.e., Attention-based Multi-view Variational Auto-Encoder (AMVAE), to incorporate both the link information and the multimodal contents for more effective and efficient embedding. Specifically, we adopt LSTM with attention model to learn the correlation between different data modalities, such as the correlation between visual regions and the specific words, to obtain the semantic embedding of the multimodal contents. Then, the link information and the semantic embedding are considered as two correlated views. A multi-view correlation learning based Variational Auto-Encoder (VAE) is proposed to learn the representation of each node, in which the embedding of link information and multimodal contents are integrated and mutually reinforced. Experiments on three real-world datasets demonstrate the superiority of the proposed model in two applications, i.e., multi-label classification and link prediction.

Recently, learning a joint representation for the multimodal data (e.g., containing both visual content and text description) has attracted extensive research interests. Usually, the features of different modalities are correlational and compositive, and thus a joint representation capturing the correlation is more effective than a subset of the features. Most of existing multimodal representation learning methods suffer from lack of additional constraints to enhance the robustness of the learned representations. In this paper, a novel Adversarial Attention Networks (AAN) is proposed to incorporate both the attention mechanism and the adversarial networks for effective and robust multimodal representation learning. Specifically, a visual-semantic attention model with siamese learning strategy is proposed to encode the fine-grained correlation between visual and textual modalities. Meanwhile, the adversarial learning model is employed to regularize the generated representation by matching the posterior distribution of the representation to the given priors. Then, the two modules are incorporated into a integrated learning framework to learn the joint multimodal representation. Experimental results in two tasks, i.e., multi-label classification and tag recommendation, show that the proposed model outperforms state-of-the-art representation learning methods.

This article describes how recently, many new technologies have been introduced to the web; linked data is probably the most important. Individuals and organizations started emerging and publishing their data on the web adhering to a set of best practices. This data is published mostly in English; hence, only English agents can consume it. Meanwhile, although the number of Arabic users on the web is immense, few Arabic datasets are published. Publication catalogs are one of the primary sources of Arabic data that is not being exploited. Arabic catalogs provide a significant amount of meaningful data and metadata that are commonly stored in excel sheets. In this article, an effort has been made to help publishers easily and efficiently share their catalogs' data as linked data. Marefa is the first tool implemented that automatically extracts RDF triples from Arabic catalogs, aligns them to the BIBO ontology and links them with the Arabic chapter of DBpedia. An evaluation of the framework was conducted, and some statistical measures were generated during the different phases of the extraction process.

Landmark retrieval is to return a set of images with their landmarks similar to those of the query images. Existing studies on landmark retrieval focus on exploiting the geometries of landmarks for visual similarity matches. However, the visual content of social images is of large diversity in many landmarks, and also some images share common patterns over different landmarks. On the other side, it has been observed that social images usually contain multimodal contents, i.e., visual content and text tags, and each landmark has the unique characteristic of both visual content and text content. Therefore, the approaches based on similarity matching may not be effective in this environment. In this paper, we investigate whether the geographical correlation among the visual content and the text content could be exploited for landmark retrieval. In particular, we propose an effective multimodal landmark classification paradigm to leverage the multimodal contents of social image for landmark retrieval, which integrates feature refinement and landmark classifier with multimodal contents by a joint model. The geo-tagged images are automatically labeled for classifier learning. Visual features are refined based on low rank matrix recovery, and multimodal classification combined with group sparse is learned from the automatically labeled images. Finally, candidate images are ranked by combining classification result and semantic consistence measuring between the visual content and text content. Experiments on real-world datasets demonstrate the superiority of the proposed approach as compared to existing methods.

In the design of differentially private mechanisms, it is usually assumed that a uniformly random source is available. However, in many situations it seems unrealistic, and one must deal with various imperfect random sources. Dodis et al. (CRYPTO'12) presented that differential privacy can be achieved with Santha-Vazirani (SV) sources, introduced in 1986, via adding a stronger property called SV-consistent sampling and left open the question if differential privacy is possible with more realistic, i.e., less structured, sources. A new source, called bias-control limited (BCL) source, introduced by Dodis (ICALP'01), is more realistic. It can be considered as a generalization of the SV and sequential bit-fixing sources. Unfortunately, the natural extension of SV-consistent sampling to the BCL source is hopeless to achieve differential privacy, mainly because SV-consistent sampling requires “consecutive” strings, while some strings cannot be generated from “non-trivial” BCL sources. Moreover, there exists some inconsistency in the bit lengths of random sources between the mechanism construction and the proofs for differentially privacy presented by Dodis et al. (CRYPTO'12). More appropriate mechanisms and more rigourous proofs are needed. Motivated by these questions, we introduce a new appealing property, called compact BCL-consistent sampling, the degeneration of which is different from SV-consistent sampling shown by Dodis et al. (CRYPTO'12). We prove that if the mechanism based on the BCL source satisfies this property, then it is differentially private for certain parameters. Even if the BCL source is degenerated into the SV source, our proof is much more intuitive and simpler than that of Dodis et al. Further, we construct an explicit finite-precision mechanism using an improved construction of infinite mechanism and a new truncation technique. We also propose its concrete results for differential privacy and utility, one core proof step of which is trickier and much shorter than the counterpart by Dodis et al. (CRYPTO'12). While the results of Dodis and Yao (CRYPTO'15) imply that if there exist differentially private mechanisms for imperfect randomness, then the parameters should have some constraints, we show an explicit construction of such mechanisms, whose parameters match the prior constraints.

We present a general solution towards building task-oriented dialogue systems for online shopping, aiming to assist online customers in completing various purchase-related tasks, such as searching products and answering questions, in a natural language conversation manner. As a pioneering work, we show what & how existing NLP techniques, data resources, and crowdsourcing can be leveraged to build such task-oriented dialogue systems for E-commerce usage. To demonstrate its effectiveness, we integrate our system into a mobile online shopping app. To the best of our knowledge, this is the first time that an AI bot in Chinese is practically used in online shopping scenario with millions of real consumers. Interesting and insightful observations are shown in the experimental part, based on the analysis of human-bot conversation log. Several current challenges are also pointed out as our future directions.

We study response selection for multiturn conversation in retrieval-based chatbots.Existing work either concatenates utterances in context or matches a response with a highly abstract context vector finally, which may lose relationships among utterances or important contextual information.We propose a sequential matching network (SMN) to address both problems.SMN first matches a response with each utterance in the context on multiple levels of granularity, and distills important matching information from each pair as a vector with convolution and pooling operations.The vectors are then accumulated in a chronological order through a recurrent neural network (RNN) which models relationships among utterances.The final matching score is calculated with the hidden states of the RNN.An empirical study on two public data sets shows that SMN can significantly outperform stateof-the-art methods for response selection in multi-turn conversation.

Connections between relations in relation extraction, which we call class ties, are common.In distantly supervised scenario, one entity tuple may have multiple relation facts.Exploiting class ties between relations of one entity tuple will be promising for distantly supervised relation extraction.However, previous models are not effective or ignore to model this property.In this work, to effectively leverage class ties, we propose to make joint relation extraction with a unified model that integrates convolutional neural network (CNN) with a general pairwise ranking framework, in which three novel ranking loss functions are introduced.Additionally, an effective method is presented to relieve the severe class imbalance problem from NR (not relation) for model training.Experiments on a widely used dataset show that leveraging class ties will enhance extraction and demonstrate the effectiveness of our model to learn class ties.Our model outperforms the baselines significantly, achieving stateof-the-art performance.

Many popular modern processors include an important hardware security feature in the form of a DRTM (Dynamic Root of Trust for Measurement) that helps bootstrap trust and resists software attacks. However, despite substantial body of prior research on trust establishment, security of DRTM was treated without involvement of the human user, who represents a vital missing link. The basic challenge is: how can a human user determine whether an expected DRTM is currently active on her device?

As an effective way of learning node representations in networks, network embedding has attracted increasing research interests recently. Most existing approaches use shallow models and only work on static networks by extracting local or global topology information of each node as the algorithm input. It is challenging for such approaches to learn a desirable node representation on incomplete graphs with a large number of missing links or on dynamic graphs with new nodes joining in. It is even challenging for them to deeply fuse other types of data such as node properties into the learning process to help better represent the nodes with insufficient links. In this paper, we for the first time study the problem of network embedding on incomplete networks. We propose a Multi-View Correlation-learning based Deep Network Embedding method named MVC-DNE to incorporate both the network structure and the node properties for more effectively and efficiently perform network embedding on incomplete networks. Specifically, we consider the topology structure of the network and the node properties as two correlated views. The insight is that the learned representation vector of a node should reflect its characteristics in both views. Under a multi-view correlation learning based deep autoencoder framework, the structure view and property view embeddings are integrated and mutually reinforced through both self-view and cross-view learning. As MVC-DNE can learn a representation mapping function, it can directly generate the representation vectors for the new nodes without retraining the model. Thus it is especially more efficient than previous methods. Empirically, we evaluate MVC-DNE over three real network datasets on two data mining applications, and the results demonstrate that MVC-DNE significantly outperforms state-of-the-art methods.

Estimating urban traffic conditions of an arterial network with GPS probe data is a practically important while substantially challenging problem, and has attracted increasing research interests recently. Although GPS probe data is becoming a ubiquitous data source for various traffic related applications currently, they are usually insufficient for fully estimating traffic conditions of a large arterial network due to the low sampling frequency. To explore other data sources for more effectively computing urban traffic conditions, we propose to collect various traffic events such as traffic accident and jam from social media as complementary information. In addition, to further explore other factors that might affect traffic conditions, we also extract rich auxiliary information including social events, road features, Point of Interest (POI), and weather. With the enriched traffic data and auxiliary information collected from different sources, we first study the traffic co-congestion pattern mining problem with the aim of discovering which road segments geographically close to each other are likely to co-occur traffic congestion. A search tree based approach is proposed to efficiently discover the co-congestion patterns. These patterns are then used to help estimate traffic congestions and detect anomalies in a transportation network. To fuse the multisourced data, we finally propose a coupled matrix and tensor factorization model named TCE_R to more accurately complete the sparse traffic congestion matrix by collaboratively factorizing it with other matrices and tensors formed by other data. We evaluate the proposed model on the arterial network of downtown Chicago with 1,257 road segments whose total length is nearly 700 miles. The results demonstrate the superior performance of TCE_R by comprehensive comparison with existing approaches.

We study tag recommendation for questions in community question answering (CQA). Tags represent the semantic summarization of questions are useful for navigation and expert finding in CQA and can facilitate content consumption such as searching and mining in these web sites. The task is challenging, as both questions and tags are short and a large fraction of tags are tail tags which occur very infrequently. To solve these problems, we propose matching questions and tags not only by themselves, but also by similar questions and similar tags. The idea is then formalized as a model in which we calculate question-tag similarity using a linear combination of similarity with similar questions and tags weighted by tag importance.Question similarity, tag similarity, and tag importance are learned in a supervised random walk framework by fusing multiple features. Our model thus can not only accurately identify question-tag similarity for head tags, but also improve the accuracy of recommendation of tail tags. Experimental results show that the proposed method significantly outperforms state-of-the-art methods on tag recommendation for questions. Particularly, it improves tail tag recommendation accuracy by a large margin.

Previous work for relation extraction from free text is mainly based on intra-sentence information. As relations might be mentioned across sentences, inter-sentence information can be leveraged to improve distantly supervised relation extraction. To effectively exploit inter-sentence information, we propose a ranking based approach, which first learns a scoring function based on a listwise learning-to-rank model and then uses it for multi-label relation extraction. Experimental results verify the effectiveness of our method for aggregating information across sentences. Additionally, to further improve the ranking of high-quality extractions, we propose an effective method to rank relations from different entity pairs. This method can be easily integrated into our overall relation extraction framework, and boosts the precision significantly.

Most current chatbot engines are designed to reply to user utterances based on existing utterance-response (or Q-R) 1 pairs.In this paper, we present DocChat, a novel information retrieval approach for chatbot engines that can leverage unstructured documents, instead of Q-R pairs, to respond to utterances.A learning to rank model with features designed at different levels of granularity is proposed to measure the relevance between utterances and responses directly.We evaluate our proposed approach in both English and Chinese: (i) For English, we evaluate Doc-Chat on WikiQA and QASent, two answer sentence selection tasks, and compare it with state-of-the-art methods.Reasonable improvements and good adaptability are observed.(ii) For Chinese, we compare DocChat with XiaoIce 2 , a famous chitchat engine in China, and side-by-side evaluation shows that DocChat is a perfect complement for chatbot engines using Q-R pairs as main source of responses.

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task is challenging, as messages in a conversational environment are short and informal, and evidence that can indicate a message is context dependent is scarce. After a study of social conversation data crawled from the web, we observed that some characteristics estimated from the responses of messages are discriminative for identifying context dependent messages. With the characteristics as weak supervision, we propose using a Long Short Term Memory (LSTM) network to learn a classifier. Our method carries out text representation and classifier learning in a unified framework. Experimental results show that the proposed method can significantly outperform baseline methods on accuracy of classification.

This paper studies the novel problem of more accurately estimating urban traffic congestions by integrating sparse probe data and traffic related information collected from social media. Limited by the lack of reliability and low sampling frequency of GPS probes, probe data are usually not sufficient for fully estimating traffic conditions of a large arterial network. To address the data sparsity challenge, we extensively collect and model traffic related data from multiple data sources. Besides the GPS probe data, we also extensively collect traffic related tweets that report various traffic events such as congestion, accident, and road construction from both traffic authority accounts and general user accounts from Twitter. To further explore other factors that might affect traffic conditions, we also extract auxiliary information including road congestion correlations, social events, road features, as well as point of interest (POI) for help. To integrate the different types of data coming from different sources, we finally propose a coupled matrix and tensor factorization model to more accurately complete the very sparse traffic congestion matrix by collaboratively factorizing it with other matrices and tensors formed by other data. We evaluate the proposed model on the arterial network of downtown Chicago with 1257 road segments. The results demonstrate the effectiveness and efficiency of the proposed model by comparison with previous approaches.

We study the problem of question retrieval in community question answering (CQA). The biggest challenge within this task is lexical gaps between questions since similar questions are usually expressed with different but semantically related words. To bridge the gaps, state-of-the-art methods incorporate extra information such as word-to-word translation and categories of questions into the traditional language models. We find that the existing language model based methods can be interpreted using a new framework, that is they represent words and question categories in a vector space and calculate question-question similarities with a linear combination of dot products of the vectors. The problem is that these methods are either heuristic on data representation or difficult to scale up. We propose a principled and efficient approach to learning representations of data in CQA. In our method, we simultaneously learn vectors of words and vectors of question categories by optimizing an objective function naturally derived from the framework. In question retrieval, we incorporate learnt representations into traditional language models in an effective and efficient way. We conduct experiments on large scale data from Yahoo! Answers and Baidu Knows, and compared our method with state-of-the-art methods on two public data sets. Experimental results show that our method can significantly improve on baseline methods for retrieval relevance. On 1 million training data, our method takes less than 50 minutes to learn a model on a single multicore machine, while the translation based language model needs more than 2 days to learn a translation table on the same machine.

In ideality, cryptographic primitives take for granted that the secret sources are derived from uniform distribution. However, in reality, we may only obtain some ‘weak’ random sources guaranteed with high unpredictability (e.g. biometric data, physical sources, and secrets with partial leakage). Formally, the security of cryptographic primitives is measured by the expectation of some function, called ‘perfect’ expectation in the ideal model and ‘weak’ expectation in the real model. The authors propose some elementary inequalities which show that the ‘weak’ expectation is not much worse than the ‘perfect’ expectation. The authors present how to overcome weak expectations dependent on the Rényi entropy other than the min and collision entropies by Dodis and Yu [TCC 2013]. The authors achieve these results by capturing on two approaches: one is by observing a new relationship between the collision entropy and other Rényi entropy, the other is by developing the connection between different moments of a variable. Furthermore, pseudorandom generator, and pairwise independent hash function family, the authors extend key derivation functions based on the Rényi entropy. The results are applied to all unpredictability applications and ‘square‐friendly’ indistinguishability applications including CPA‐secure symmetric‐key encryption schemes.

With the availability of cheap location sensors, geotagging of images in online social media is very popular. With a large amount of geo-tagged social images, it is interesting to study how these images are shared across geographical regions and how the geographical language characteristics and vision patterns are distributed across different regions. Unlike textual document, geo-tagged social image contains multiple types of content, i.e., textual description, visual content, and geographical information. Existing approaches usually mine geographical characteristics using a subset of multiple types of image contents or combining those contents linearly, which ignore correlations between different types of contents, and their geographical distributions. Therefore, in this paper, we propose a novel method to discover geographical characteristics of geo-tagged social images using a geographical topic model called geographical topic model of social images (GTMSIs). GTMSI integrates multiple types of social image contents as well as the geographical distributions, in which image topics are modeled based on both vocabulary and visual features. In GTMSI, each region of the image would have its own topic distribution, and hence have its own language model and vision pattern. Experimental results show that our GTMSI could identify interesting topics and vision patterns, as well as provide location prediction and image tagging.

Scientific literature ranking is essential to help researchers find valuable publications from a large literature collection. Recently, with the prevalence of webpage ranking algorithms such as PageRank and HITS, graph-based algorithms have been widely used to iteratively rank papers and researchers through the networks formed by citation and coauthor relationships. However, existing graph-based ranking algorithms mostly focus on ranking the current importance of literature. For researchers who enter an emerging research area, they might be more interested in new papers and young researchers that are likely to become influential in the future, since such papers and researchers are more helpful in letting them quickly catch up on the most recent advances and find valuable research directions. Meanwhile, although some works have been proposed to rank the prestige of a certain type of objects with the help of multiple networks formed of multiobjects, there still lacks a unified framework to rank multiple types of objects in the bibliographic network simultaneously. In this article, we propose a unified ranking framework MRCoRank to corank the future popularity of four types of objects: papers, authors, terms, and venues through mutual reinforcement. Specifically, because the citation data of new publications are sparse and not efficient to characterize their innovativeness, we make the first attempt to extract the text features to help characterize innovative papers and authors. With the observation that the current trend is more indicative of the future trend of citation and coauthor relationships, we then construct time-aware weighted graphs to quantify the importance of links established at different times on both citation and coauthor graphs. By leveraging both the constructed text features and time-aware graphs, we finally fuse the rich information in a mutual reinforcement ranking framework to rank the future importance of multiobjects simultaneously. We evaluate the proposed model through extensive experiments on the ArnetMiner dataset containing more than 1,500,000 papers. Experimental results verify the effectiveness of MRCoRank in coranking the future influence of multiobjects in a bibliographic network.

Interpreting the user intent in search queries is a key task in query understanding. Query intent classification has been widely studied. In this article, we go one step further to understand the query from the view of head--modifier analysis. For example, given the query “popular iphone 5 smart cover,” instead of using coarse-grained semantic classes (e.g.,find electronic product), we interpret that “smart cover” is the head or the intent of the query and “iphone 5” is its modifier. Query head--modifier detection can help search engines to obtain particularly relevant content, which is also important for applications such as ads matching and query recommendation. We introduce an unsupervised semantic approach for query head--modifier detection. First, we mine a large number of instance level head--modifier pairs from search log. Then, we develop a conceptualization mechanism to generalize the instance level pairs to concept level. Finally, we derive weighted concept patterns that are concise, accurate, and have strong generalization power in head--modifier detection. The developed mechanism has been used in production for search relevance and ads matching. We use extensive experiment results to demonstrate the effectiveness of our approach.

Image location prediction is used to estimate the geolocation where an image is taken, which is important for many image applications, such as image retrieval, image browsing, and organization. Since a social image contains heterogeneous contents, such as visual content and textual content, effectively incorporating these contents to predict location is nontrivial. Moreover, it is observed that image content patterns and the locations where they may appear correlate hierarchically. Traditional image location prediction methods mainly adopt a single-level architecture and assume images are independently distributed in geographical space, which is not directly adaptable to the hierarchical correlation. In this paper, we propose a geographically hierarchical bi-modal deep belief network (GH-BDBN) model, which is a compositional learning architecture that integrates multi-modal deep learning model with a non-parametric hierarchical prior model. GH-BDBN learns a joint representation capturing the correlations among different types of image content using a bi-modal DBN, with a geographically hierarchical prior over the joint representation to model the hierarchical correlation between image content and location. Then, an efficient inference algorithm is proposed to learn the parameters and the geographical hierarchical structure of geographical locations. Experimental results demonstrate the superiority of our model for image location prediction.

Studying the bursty nature of cascades in social media is practically important in many applications such as product sales prediction, disaster relief, and stock market prediction. Although the cascade volume prediction has been extensively studied, how to predict when a burst will come remains an open problem. It is challenging to predict the time of the burst due to the ``quick rise and fall'' pattern and the diverse time spans of the cascades. To this end, this paper proposes a classification based approach for burst time prediction by utilizing and modeling rich knowledge in information diffusion. Particularly, we first propose a time window based approach to predict in which time window the burst will appear. This paves the way to transform the time prediction task to a classification problem. To address the challenge that the original time series data of the cascade popularity only are not sufficient for predicting cascades with diverse magnitudes and time spans, we explore rich information diffusion related knowledge and model them in a scale-independent manner. Extensive experiments on a Sina Weibo reposting dataset demonstrate the superior performance of the proposed approach in accurately predicting the burst time of posts.

This paper proposes mining query subtopics from questions in community question answering (CQA). The subtopics are represented as a number of clusters of questions with keywords summarizing the clusters. The task is unique in that the subtopics from questions can not only facilitate user browsing in CQA search, but also describe aspects of queries from a question-answering perspective. The challenges of the task include how to group semantically similar questions and how to find keywords capable of summarizing the clusters. We formulate the subtopic mining task as a non-negative matrix factorization (NMF) problem and further extend the model of NMF to incorporate question similarity estimated from metadata of CQA into learning. Compared with existing methods, our method can jointly optimize question clustering and keyword extraction and encourage the former task to enhance the latter. Experimental results on large scale real world CQA datasets show that the proposed method significantly outperforms the existing methods in terms of keyword extraction, while achieving a comparable performance to the state-of-the-art methods for question clustering.

Conventional traffic congestion estimation approaches require the deployment of traffic sensors or large-scale probe vehicles. The high cost of deploying and maintaining these equipments largely limits their spatial-temporal coverage. This paper proposes an alternative solution with lower cost and wider spatial coverage by exploring traffic related information from Twitter. By regarding each Twitter user as a traffic monitoring sensor, various real-time traffic information can be collected freely from each corner of the city. However, there are two major challenges for this problem. Firstly, the congestion related information extracted directly from real-time tweets are very sparse due both to the low resolution of geographic location mentioned in the tweets and the inherent sparsity nature of Twitter data. Secondly, the traffic event information coming from Twitter can be multi-typed including congestion, accident, road construction, etc. It is non-trivial to model the potential impacts of diverse traffic events on traffic congestion. We propose to enrich the sparse real-time tweets from two directions: 1) mining the spatial and temporal correlations of the road segments in congestion from historical data, and 2) applying auxiliary information including social events and road features for help. We finally propose a coupled matrix and tensor factorization model to effectively integrate rich information for Citywide Traffic Congestion Eestimation (CTCE). Extensive evaluations on Twitter data and 500 million public passenger buses GPS data on nearly 700 mile roads of Chicago demonstrate the efficiency and effectiveness of the proposed approach.

The vast amount of geo-tagged social images has attracted great attention in research of predicting location using the plentiful content of images, such as visual content and textual description. Most of the existing researches use the text-based or vision-based method to predict location. There still exists a problem: how to effectively exploit the correlation between different types of content as well as their geographical distributions for location prediction. In this paper, we propose to predict image location by learning the latent relation between geographical location and multiple types of image content. In particularly, we propose a geographical topic model GTMSI (geographical topic model of social image) to integrate multiple types of image content as well as the geographical distributions. In GTMI, image topic is modeled on both text vocabulary and visual feature. Each region has its own distribution over topics and hence has its own language model and vision pattern. The location of a new image is estimated based on the joint probability of image content and similarity measure on topic distribution between images. Experiment results demonstrate the performance of location prediction based on GTMSI.

As the most popular platform, Android dominates the mobile device market. In order to enrich the functions of the phone and facilitate the utilization of users, more and more Android applications have been developed. Unfortunately, a greatly increasing amount of malware targeting the Android platform mingle with the numerous benign applications and hide in almost every market, even the official market Google Play. Therefore, it is a pressing concern about how to measure and assess the risk of such apps. In this paper, we propose a novel approach to deal with this problem. First of all, through the empirical analysis with market-scale dataset, we verify the following fact: for a set of benign applications in the same category, the type and number of permissions they request are similar and consistent in general. Hence, for the benign applications in each category, we can construct a standard permission vector model, which can be used as a baseline to measure and assess the risk of applications in the category. For a downloaded app, we extract its requested permissions to form a permission vector, whose deviation from the baseline can be calculated by employing Euclidean distance and weighted Euclidean distance. The deviation can be used as metric to measure and assess the risk of the app. Finally, an experiment on real-world dataset, consisting of 7737 market apps and 1260 malware samples, is conducted to evaluate our method. The empirical result validates the effectiveness of our approach to help users understand the risk when they decide to install an app.

Transferable electronic cash (e-cash) allows the recipient of a coin in a transaction to transfer it in a later payment transaction to the third person. The transferability is a desirable property in many applications. However, in the existing transferable e-cash, the size of coins is constant at the cost of increasing the users' burden and not satisfying the optimal anonymity. On the other hand, the e-cash protocol with optimal anonymity has the drawback that the size of coins grows linearly in the number of transfers. In this paper, a transferable optimal-size e-cash is proposed using a different structure, that is, coins are divided into two parts. The new scheme achieves the optimal anonymity, i.e., it satisfies Observe-then-Receive Full Anonymity (OtR-FA), Spend-then-Observe Full Anonymity (StO-FA) and Spend-then-Receive Full Anonymity (StR-FA). Meanwhile, the users has not to keep in memory the data associated to all past transactions. At last, the security proof of the new scheme is given in the standard model.

Affiliation-Hiding Authenticated Asymmetric Group Key Agreement (AH-AAGKA) protocol can be utilized by the members of a group to authenticate each other secretly. The participants affiliated to the group can execute the AH-AAGKA protocol to establish a common encryption key. Any legitimate participant can compute its own decryption key corresponding to the encryption key. Particularly, every legitimate player's affiliation information is only revealed to other legitimate players. In this paper, we present a one-round AH-AAGKA protocol. Compared with previous work, in our protocol, Group Authority (GA) does not need to be fully trusted (we call it semi-trusted). Therefore, GA cannot impersonate any honest user to execute the protocol. Meanwhile, GA can trace group members through analyzing the communication flows. Our protocol holds the affiliation-hiding property and detectability. Additionally, our scheme exhibits Perfect Forward Secrecy for both GA and outside attackers.

Transferable conditional electronic‐cash (e‐cash) allows the recipient of a coin in a transaction to transfer it in a later payment transaction to the third person based on the outcome not known in advance. Anonymity is a very important property for a transferable conditional e‐cash. However, none of the existed transferable conditional e‐cash achieve the optimal anonymity because of its special structure, that is, introducing transferability in the conditional e‐cash. In this study, they novelly present a transferable conditional e‐cash scheme using a totally different structure, that is, adding condition into the transferable e‐cash. Thanks to employing Groth–Sahai proofs systems and commuting signatures, the new transferable conditional e‐cash satisfies optimal anonymity. Accordingly, they present an extended security model by introducing a publisher who is responsible for publishing two outcomes of a condition. Then, they prove the new scheme's security in the standard model. Compared with the existing transferable conditional e‐cash, the efficiency of the new scheme is also improved since the size of the computation and communication is constant.

We study the use of temporal information in the form of timelines to enhance multidocument summarization.We employ a fully automated temporal processing system to generate a timeline for each input document.We derive three features from these timelines, and show that their use in supervised summarization lead to a significant 4.1% improvement in ROUGE performance over a state-of-the-art baseline.In addition, we propose TIMEMMR, a modification to Maximal Marginal Relevance that promotes temporal diversity by way of computing time span similarity, and show its utility in summarizing certain document sets.We also propose a filtering metric to discard noisy timelines generated by our automatic processes, to purify the timeline input for summarization.By selectively using timelines guided by filtering, overall summarization performance is increased by a significant 5.9%.

Most existing approaches for text classification represent texts as vectors of words, namely ``Bag-of-Words.'' This text representation results in a very high dimensionality of feature space and frequently suffers from surface mismatching. Short texts make these issues even more serious, due to their shortness and sparsity. In this paper, we propose using ``Bag-of-Concepts'' in short text representation, aiming to avoid the surface mismatching and handle the synonym and polysemy problem. Based on ``Bag-of-Concepts,'' a novel framework is proposed for lightweight short text classification applications. By leveraging a large taxonomy knowledgebase, it learns a concept model for each category, and conceptualizes a short text to a set of relevant concepts. A concept-based similarity mechanism is presented to classify the given short text to the most similar category. One advantage of this mechanism is that it facilitates short text ranking after classification, which is needed in many applications, such as query or ad recommendation. We demonstrate the usage of our proposed framework through a real online application: Channel-based Query Recommendation. Experiments show that our framework can map queries to channels with a high degree of precision (avg. precision=90.3%), which is critical for recommendation applications.

Previous work studied one-class collaborative filtering (OCCF) problems including pointwise methods, pairwise methods, and content-based methods. The fundamental assumptions made on these approaches are roughly the same. They regard all missing values as negative. However, this is unreasonable since the missing values actually are the mixture of negative and positive examples. A user does not give a positive feedback on an item probably only because she/he is unaware of the item, but in fact, she/he is fond of it. Furthermore, content-based methods, e.g. collaborative topic regression (CTR), usually require textual content information of items. This cannot be satisfied in some cases. In this paper, we exploit latent Dirichlet allocation (LDA) model on OCCF problem. It assumes missing values unknown and only models the observed data, and it also does not need content information of items. In our model items are regarded as words and users are considered as documents and the user-item feedback matrix denotes the corpus. Experimental results show that our proposed method outperforms the previous methods on various ranking-oriented evaluation metrics.

This paper studies the problem of question retrieval in community question answering (CQA). To bridge lexical gaps in questions, which is regarded as the biggest challenge in retrieval, state-of-the-art methods learn translation models using answers under an assumption that they are parallel texts. In practice, however, questions and answers are far from "parallel". Indeed, they are heterogeneous for both the literal level and user behaviors. There are a particularly large number of low quality answers, to which the performance of translation models is vulnerable. To address these problems, we propose a supervised question-answer topic modeling approach. The approach assumes that questions and answers share some common latent topics and are generated in a "question language" and "answer language" respectively following the topics. The topics also determine an answer quality signal. Compared with translation models, our approach not only comprehensively models user behaviors on CQA portals, but also highlights the instinctive heterogeneity of questions and answers. More importantly, it takes answer quality into account and performs robustly against noise in answers. With the topic modeling approach, we propose a topic-based language model, which matches questions not only on a term level but also on a topic level. We conducted experiments on large scale data from Yahoo! Answers and Baidu Knows. Experimental results show that the proposed model can significantly outperform state-of-the-art retrieval models in CQA.

Kad is the most popular P2P file sharing system. Monitoring Kad peers' lookup traffic is an important work for the analysis and optimization of Peer-to-Peer (P2P) network. During the monitoring process, we find that the peer's status significantly influences the monitoring results. Each lookup action changes the searching peer's routing table status, and it may break the monitoring process. In this paper, we analyze the changes in the routing table to verify its effect on the monitoring process. If the distance between the target ID and searcher's Kad ID is in within a certain critical range, previous searches may cause future searches to fail with high probability. We estimate the boundary of this critical range. The experiments performed on eMule shows that such a critical range exist, and that deploying more than 1024 IP addresses cannot help to improve the success rate of the monitoring process.

Inferring diffusion networks from traces of cascades has been extensively studied to better understand information diffusion in many domains. A widely used assumption in previous work is that the diffusion network is homogenous and diffusion processes of cascades follow the same pattern. However, in social media, users may have various interests and the connections among them are usually multi-faceted. In addition, different cascades normally diffuse at different speeds and spread to diverse scales, and hence show various diffusion patterns. It is challenging for traditional models to capture the heterogeneous user interactions and diverse patterns of cascades in social media. In this paper, we investigate a novel problem of inferring multi-aspect diffusion networks with multi-pattern cascades. In particular, we study the effects of various diffusion patterns on the information diffusion process by analyzing users' retweeting behavior on a microblogging dataset. By incorporating aspect-level user interactions and various diffusion patterns, a new model for inferring Multi-aspect transmission Rates between users using Multi-pattern cascades (MMRate) is proposed. We also provide an Expectation Maximization algorithm to effectively estimate the parameters. Experimental results on both synthetic and microblogging datasets demonstrate the superior performance of our approach over the state-of-the-art methods in inferring multi-aspect diffusion networks.

Kad is a P2P protocol which has about 1 million concurrent online users. The eclipse attack is one of the most severe threats in Kad. In this paper, we propose a distributed verification approach to defend against the eclipse attack in Kad. Previous works mostly concentrate on ID generation or secure routing algorithm. Our approach utilizes many benign peers to prove that the storage peer is valid. The attacker has to provide massive malicious hosts and IP addresses to break our defense. In contrast, it is hard for the attacker to get these resources. Moreover, our solution could be applied to the open-source software and centralized services are not needed in our system. Simulation results show that the attacker has to get 1000 IP addresses to launch the attack successfully.

Researchers or students entering a emerging research area are particularly interested in what newly published papers will be most cited and which young researchers will become influential in the future, so that they can catch the most recent advances and find valuable research directions. However, predicting the future importance of scientific articles and authors is extremely hard due to the dynamic nature of literature networks and evolving research topics. Different from most previous studies aiming to rank the current importance of literature and authors, we focus on ranking the future popularity of new publications and young researchers by proposing a unified ranking model to combine various available information. Specifically, we first propose to use two kinds of text features, words and words co-occurrence to characterize innovative papers and authors. Then, instead of using static and un-weighted graphs, we construct time-aware weighted graphs to distinguish the various importance of links established at different time. Finally, by leveraging both the constructed text features and graphs, we propose a mutual reinforcement ranking framework called MRFRank to rank the future importance of papers and authors simultaneously. Experimental results on the ArnetMiner dataset show that the proposed approach significantly outperforms the baselines on the metric recommendation intensity.

The notion of Affiliation-Hiding Authenticated Group Key Agreement (AH-AGKA) protocols was first introduced by Jarecki et al. in CT-RSA 2007, where they presented two concrete AH-AGKA protocols. In this paper, we show that Jarecki et al.'s second protocol has some drawbacks. We propose a new affiliation-hiding protocol. Differing from Jarecki et al.'s protocol, our protocol is asymmetric. Compared with existing AH-AGKA protocols, our scheme not only exhibits the affiliation-hiding property, but also holds the properties of detectability and perfect forward secrecy.

Recent years have witnessed the tremendous development of social media, which attracts a vast number of Internet users. The high-dimension content generated by these users provides an unique opportunity to understand their behavior deeply. As one of the most fundamental topics, location estimation attracts more and more research efforts. Different from the previous literature, we find that user's location is strongly related to user interest. Based on this, we first build a detection model to mine user interest from short text. We then establish the mapping between location function and user interest before presenting an efficient framework to predict the user's location with convincing fidelity. Thorough evaluations and comparisons on an authentic data set show that our proposed model significantly outperforms the state-of-the-arts approaches. Moreover, the high efficiency of our model also guarantees its applicability in real-world scenarios.

Microblog services have emerged as an essential way to strengthen the communications among individuals and organizations. These services promote timely and active discussions and comments towards products, markets as well as public events, and have attracted a lot of attentions from organizations. In particular, emerging topics are of immediate concerns to organizations since they signal current concerns of, and feedback by their users. Two challenges must be tackled for effective emerging topic detection. One is the problem of real-time relevant data collection and the other is the ability to model the emerging characteristics of detected topics and identify them before they become hot topics. To tackle these challenges, we first design a novel scheme to crawl the relevant messages related to the designated organization by monitoring multi-aspects of microblog content, including users, the evolving keywords and their temporal sequence. We then develop an incremental clustering framework to detect new topics, and employ a range of content and temporal features to help in promptly detecting hot emerging topics. Extensive evaluations on a representative real-world dataset based on Twitter data demonstrate that our scheme is able to characterize emerging topics well and detect them before they become hot topics.

ABSTRACT In CT‐RSA 2007, Jarecki, Kim, and Tsudik introduced the notion of affiliation‐hiding authenticated group key agreement (AH‐AGKA) protocols and presented two concrete AH‐AGKA protocols. In this paper, we will show that these protocols have some drawbacks. We will also introduce the notion of affiliation‐hiding authenticated asymmetric group key agreement (AH‐AAGKA) and present an AH‐AAGKA protocol. AH‐AAGKA protocols allow the participants of a group to establish a common encryption key associated with several decryption keys; each of which can only be computed by the corresponding legitimate participant. Meanwhile, any party is assured that its affiliation is revealed to the participants that belong to the same group only. Compared with previous AH‐AGKA protocols, if invalid players participate in our protocol, legitimate participants can identify these invalid players. In contrast to existing AH‐AGKA protocols, our protocol holds perfect forward secrecy, which is proven in a novel security model we proposed. Additionally, we present a new privacy model to prove that our protocol achieves linkable affiliation‐hiding property. Copyright © 2012 John Wiley & Sons, Ltd.

Comparing one thing with another is a typical part of human decision making process. However, it is not always easy to know what to compare and what are the alternatives. In this paper, we present a novel way to automatically mine comparable entities from comparative questions that users posted online to address this difficulty. To ensure high precision and high recall, we develop a weakly supervised bootstrapping approach for comparative question identification and comparable entity extraction by leveraging a large collection of online question archive. The experimental results show our method achieves F1-measure of 82.5 percent in comparative question identification and 83.3 percent in comparable entity extraction. Both significantly outperform an existing state-of-the-art method. Additionally, our ranking results show highly relevance to user's comparison intents in web.

In this paper, we propose a survival modeling approach to promoting ranking diversity for biomedical information retrieval. The proposed approach concerns with finding relevant documents that can deliver more different aspects of a query. First, two probabilistic models derived from the survival analysis theory are proposed for measuring aspect novelty. Second, a new method using Wikipedia to detect aspects covered by retrieved documents is presented. Third, an aspect filter based on a two-stage model is introduced. It ranks the detected aspects in decreasing order of the probability that an aspect is generated by the query. Finally, the relevance and the novelty of retrieved documents are combined at the aspect level for reranking. Experiments conducted on the TREC 2006 and 2007 Genomics collections demonstrate the effectiveness of the proposed approach in promoting ranking diversity for biomedical information retrieval. Moreover, we further evaluate our approach in the Web retrieval environment. The evaluation results on the ClueWeb09-T09B collection show that our approach can achieve promising performance improvements.

Support Vector Machines (SVMs) is a popular machine learning algorithm based on Statistical Learning Theory (SLT). However, traditional solutions suffer from O(n2) time complexity. In this paper, a novel two-stage informative pattern abstraction algorithm is proposed. The first stage of the algorithm is data cleaning based on bootstrap sampling. A bundle of weak SVM classifiers are trained based on the sampled small datasets. Training data correctly classified by all the weak classifiers are cleaned. In the second stage, to further improve performance of final classifier and reduce training time, two novel informative pattern extraction algorithms based on entropy maximization SVMs are proposed. Empirical studies show our approach is effective in reducing size of training datasets and the computational cost, outperforming the state-of-the-art SVM training algorithms PEGASOS, RSVM and LIBLINEAR SVM with comparable classification accuracy.

Resampling method is a popular and effective technique to imbalanced learning. However, most resampling methods ignore data density information and may lead to overfitting. A novel adaptive over-sampling technique based on data density (ASMOBD) is proposed in this paper. Compared with existing resampling algorithms, ASMOBD can adaptively synthesize different number of new samples around each minority sample according to its level of learning difficulty. Therefore, this method makes the decision region more specific and can eliminate noise. What's more, to avoid over generalization, two smoothing methods are proposed. Cost- Sensitive learning is also an effective technique to imbalanced learning. In this paper, ASMOBD and Cost-Sensitive SVM are combined. Experiments show that our methods perform better than various state-of-art approaches on 9 UCI datasets by using metrics of G-mean and area under the receiver operation curve (AUC).

Symbolic execution simulates program execution by replacing concrete values with symbolic variables for inputs. It could be used in software behavior analysis, vulnerability detection and software security assessment. In this paper, we analyze the path explosion problem encountered in vulnerability detection with the state-of-the-art symbolic execution technology for large scale file parsing programs. We also propose 4 alleviations to ease the problem, i.e. loop controlling, irrelevant path elimination, path selecting and parallel symbolic execution. Based on these alleviations, we implemented a prototype tool to detect file parsing vulnerability in large scale programs automatically, and evaluate it with a suit of benchmarks chosen from open source programs. Our tool detected not only all reported vulnerabilities of memory overflow in the benchmarks, but also some unreported vulnerabilities. The evaluation results show these alleviations could effectively ease the path explosion problem while analyzing large scale file parsing programs.

We introduce the concept of Affiliation-Hiding Authenticated Asymmetric Group Key Agreement (AH-AAGKA) and construct a concrete one-round AH-AAGKA protocol. An AH-AAGKA protocol allows the participants of a group to establish a common encryption key associated with several decryption keys; each of which can only be computed by the corresponding legitimate group member. An AH-AAGKA protocol has the following privacy feature. For a member 𝒰i of a group G, if 𝒰i participates in an AH-AAGKA protocol, any protocol participant 𝒰j cannot learn whether 𝒰i is a member of G, unless 𝒰j himself is a member of group G. Our scheme demonstrates new features in comparison with other existing AH-AGKA protocols. If non-group members participate in our protocol, honest parties can identify these non-group members. Our scheme also captures Unlinkability and Perfect Forward Secrecy (PFS), which are missing in other existing schemes. We propose a novel security model to prove that our protocol holds PFS and present a new privacy model to prove that our scheme meets Affiliation-Hiding property.

In this paper, we propose an approach based on a topic generative model called Latent Dirichlet Allocation (LDA) to promoting ranking diversity for biomedical information retrieval. Different from other approaches or models which consider aspects on word level, our approach assumes that aspects should be identified by the topics of retrieved documents. We present LDA model to discover topic distribution of retrieval passages and word distribution of each topic dimension, and then re-rank retrieval results with topic distribution similarity between passages based on JV-size slide window. Experiments on TREC 2007 Genomics collection and two distinctive IR baseline runs demonstrate the effectiveness of our method in promoting ranking diversity for biomedical information retrieval. Evaluation results show that our approach can achieve 8% improvement over the highest Aspect MAP reported in TREC 2007 Genomics track.

This paper is concerned with the problem of question recommendation in the setting of Community Question Answering (CQA). Given a question as query, our goal is to rank all of the retrieved questions according to their likelihood of being good recommendations for the query. In this paper, we propose a notion of public interest, and show how public interest can boost the performance of question recommendation. In particular, to model public interest in question recommendation, we build a language model to combine relevance score to the query and popularity score regarding question popularity. Experimental results on Yahoo!Answers dataset demonstrate the performance of question recommendation can be greatly improved with considering the public interest.

In statistical machine translation, the number of sentence pairs in the bilingual corpus is very important to the quality of translation. However, when the quantity reaches some extent, enlarging corpus has less effect on the translation, whereas increasing greatly the time and space complexity to building translation systems, which hinders the development of statistical machine translation. In this paper, we propose several ranking approaches to measure the quantity of information of each sentence pair, and apply them into a graph-based bilingual corpus selection framework to form an improved corpus selection approach, which now considers the difference of the initial quantities of information between the sentence pairs. Our experiments in a Chinese-English translation task show that, selecting only 50% of the whole corpus via the graph-based selection approach as training set, we can obtain the near translation result with the one using the whole corpus, and we obtain better results than the baselines after using the IDF-related ranking approach.

Video recommendation is an important approach for helping people to access interesting videos. In this paper, we propose a scheme to integrate rich information for video recommendation. We regard video recommendation as a ranking problem and generate multiple ranking lists by exploring different information sources. A multi-task rank aggregation approach is proposed to integrate the ranking lists for different users in a joint manner. Our scheme is flexible and can easily incorporate other methods by adding their generated ranking lists into our multi-task learning algorithm. We conduct experiments with 76 users and more than 10,000 videos. The results demonstrate the feasibility and effectiveness of our approach.

Web applications are vulnerable targets of security attacks. Among the well known attack type - XSS(Cross-Site Scripting), the most threatening is Stored XSS. Since most static analysis methods refer to Reflected XSS but few concentrate on Stored XSS which is more devastating, plus the fact that pure static analysis offers high false positive rate, we present a static Stored XSS detection algorithm integrated with program slicing method to generate the slices of web application related to possible Stored XSS. The slices are composed of two parts, threat injection and threat release, which reconstruct a Stored XSS attack scenario. They are of great value for later manual checking or other dynamic analysis. For manual checking, the programmer can directly check the code related to possible vulnerabilities. For dynamic analysis or model checking, the program coverage can be large or even complete because of the small size of these slices.

BACKGROUND: In the biomedical domain, the desired information of a question (query) asked by biologists usually is a list of a certain type of entities covering different aspects that are related to the question, such as genes, proteins, diseases, mutations, etc. Hence it is important for a biomedical information retrieval system to be able to provide comprehensive and diverse answers to fulfill biologists' information needs. However, traditional retrieval models assume that the relevance of a document is independent of the relevance of other documents. This assumption may result in high redundancy and low diversity in the retrieval ranked lists. RESULTS: In this paper, we propose a relevance-novelty combined model, named RelNov model, based on the framework of an undirected graphical model. It consists of two component models, namely the aspect-term relevance model and the aspect-term novelty model. They model the relevance of a document and the novelty of a document respectively. We show that our approach can achieve 16.4% improvement over the highest aspect level MAP reported in the TREC 2007 Genomics track, and 9.8% improvement over the highest passage level MAP reported in the TREC 2007 Genomics track. CONCLUSIONS: The proposed combination model which models aspects, terms, topic relevance and document novelty as potential functions is demonstrated to be effective in promoting ranking diversity as well as in improving relevance of ranked lists for genomics search. We also show that the use of aspect plays an important role in the model. Moreover, the proposed model can integrate various different relevance and novelty measures easily.

Cloud computing, as a newly emergent computing environment, promises dynamic flexible infrastructures required to host Internet applications and application service level objects (SLOs) guaranteed services in a pay-as-you-go manner to the public. However, an important problem that remains to be effectively addressed is how to offer a cloud resource management solution that saves hardware and operations and management costs while meeting various SLOs. It faces the following challenges: complex dynamic relationships between application workload and SLOs and resource utilization, and the virtual machine (VM) placement problem in cloud environments. In this paper, we present an integrated approach that employs three-layered resource controllers using different analytic techniques, including the feedback control theory, statistical machine learning and system identification etc. Compared with Xen, KVM is chosen as the VM monitor to implement the proposed approach. Our experimental results show that the integration of layered controllers can reasonably allocate multiple resources to applications which execute on different VMs in cloud environments to achieve application SLOs under fluctuating time-varying workloads and unpredictable variations of system situations. In addition, it provides application SLO differentiation.

Identity (ID) uniqueness is essential in distributed hash table (DHT)-based systems, as peer lookup and resource searching rely on ID matching. However, many DHT implementations in the wild, such as Kad and Mainline, do not enforce such uniqueness. Most previous works and measurements on DHTs do not take into account that IDs among peers may not be unique. Unfortunately, we observe that a significant portion of peers, i.e. 19.5% of the peers in Kad and 4.0% of the peers in Mainline, do not have unique IDs. These repetitions would mislead the measurements and modeling on those networks. We further focus on investigating the repetition in Kad considering its wider usage and more serious situation of repetition. We observe that there are a large number of peers that frequently change their UDP ports, and there are a few IDs that repeat for a large number of times and all peers with these IDs do not respond to Kad protocol. We also analyze the effects of ID repetitions under simplified settings and find that the current repetition degrades Kad's performance on publishing and searching, but has insignificant effect on lookup process. These measurement and analysis are useful to further determine the sources of repetitions and are also useful for finding suitable parameters in publishing and searching processes in DHT networks without compulsive ID uniqueness.

Formal concept analysis and rough set analysis are two complementary approaches for analyzing data. This paper studies approaches to constructing fuzzy concept lattices based on generalized fuzzy rough approximation operators. For a residual implicat

In the research area of community-based question and answering (cQA) services such as Yahoo! Answers, reuse of the answers has attracted more and more interest. Most researchers focus on the correctness of answers and pay little attention to the completeness of answers. In this paper, we try to address the answer completeness problem for "survey questions" for which answer completeness is crucial. We propose to generate a more complete answer from replies in cQA services through a term hierarchical structure based question-oriented extractive summarization which is different from traditional query-based extractive summarization. The experimental results are very promising in terms of recall, precision and conciseness.

Abstract In the traditional identity‐based cryptography, a user, who holds multiple identities, has to manage multiple private keys, where each private key is associated with an identity. In this paper, we present a key agreement protocol, which allows a single private key to map multiple public keys (identities) that are selectable by the user. That is, the established session key is associated with an arbitrary subset of identities held by the user, while the unselected identities remain secret to other participants. As a bonus, our scheme can be considered as a credential‐based key agreement, where the unique private key can be treated as a credential of the user and the user only proves that his credential is associated with some selected identities. We prove that our scheme is secure in the random oracle model. Copyright © 2010 John Wiley & Sons, Ltd.

Both of mobile multimedia and mobile Internet are the important development directions of the mobile service. However, it would take on great cost by using the high data transmission rate of wireless multimedia communication service. Under the premise of not increasing the investment in hardware, the personalized service could be applied to the mobile service to not only reducing wireless multimedia communication cost but also keeping the quality of mobile service for users. This paper presents a kind of model on tree graph that works on server-side. And it integrates individual requirements of users in mobile terminal with recommended information resources on the Internet in order to organize multicast push. This paper explains a method of a tree model in theory, brings forward a series of correlative definitions and formulae of founding the model, and designs an Algorithm on the Tree Graph Node's Establishment and Updating. Finally, it uses an implement of well-ordered to prove strictly the algorithm's determinacy, and then, analyzes time complexity of the algorithm. On the theory, the algorithm is proved of the traits of determinacy, effectiveness and low time complexity.

Traditional retrieval models assume that the relevance of a document is independent of the relevance of other documents. However, this assumption may result in high redundancy and low diversity in a ranked list. In order to provide comprehensive and diverse answers to fulfill biologists' information need, we propose a relevance-novelty combined model, named RelNov model, based on the framework of an undirected graphical model. Experiments conducted on the TREC 2006 and 2007 Genomics collections show that the proposed approach is effective in promoting both diversity and relevance of retrieval ranked lists.

Nowadays, web servers are suffering from flash crowds and application layer DDoS attacks that can severely degrade the availability of services. It is difficult to prevent them because they comply with the communication protocol. Peer-to-peer (P2P) networks have been exploited to amplify DDoS attacks, but we believe their available resource, such as distributed storage and network bandwidth, can be used to mitigate both flash crowds and DDoS attacks. In this paper, we propose a server initiated approach to employ deployed P2P networks as distributed web caches, so that the workload directed to web servers can be reduced. In experiments, we use Kad as the particular P2P network for the realization of a large-scale distributed web cache. We performed comprehensive evaluation on the feasibility, efficiency and robustness of our scheme, through experiments and simulations on the prototype we implemented. The evaluation results show that our scheme can increase the capacity of the protected web servers at least 10 times at the same cost of connection and bandwidth consumption. The web contents cached in Kad remain reachable even under churn of peers and targeted DoS attack, and the access latency is comparable to normal direct access to web servers. It also achieves good load balancing under the heavy-tailed distribution of object popularity.

In this paper, we propose a new probabilistic generative model, called Topic-Perspective Model, for simulating the generation process of social annotations. Different from other generative models, in our model, the tag generation process is separated from the content term generation process. While content terms are only generated from resource topics, social tags are generated by resource topics and user perspectives together. The proposed probabilistic model can produce more useful information than any other models proposed before. The parameters learned from this model include: (1) the topical distribution of each document, (2) the perspective distribution of each user, (3) the word distribution of each topic, (4) the tag distribution of each topic, (5) the tag distribution of each user perspective, (6) and the probabilistic of each tag being generated from resource topics or user perspectives. Experimental results show that the proposed model has better generalization performance or tag prediction ability than other two models proposed in previous research.

In this paper, we propose a probabilistic survival model derived from the survival analysis theory for measuring aspect novelty. The retrieved documents' query-relevance and novelty are combined at the aspect level for re-ranking. Experiments conducted on the TREC 2006 and 2007 Genomics collections demonstrate the effectiveness of the proposed approach in promoting ranking diversity for biomedical information retrieval.

We present NegativeRank, a novel graph-based sentence ranking model to improve the diversity of focused summary by performing random walks over sentence graph with negative edge weights. Unlike the typical eigenvector centrality ranking, our method models the redundancy among sentence nodes as the negative edges. The negative edges can be thought of as the propagation of disapproval votes which can be used to penalize redundant sentences. As the iterative process continues, the initial ranking score of a given node will be adjusted according to a long-term negative endorsement from other sentence nodes. The evaluation results confirm that our proposed method is very effective in improving the diversity of the focused summary, compared to several well-known text summarization methods.

Biclustering methods allow us to identify genes with similar behavior with respect to different conditions. Ant colony optimization (ACO) algorithms have been shown to be effective problem solving strategies for multiple objective optimization (MOO). Multiple objective ant colony optimization (MOACO) mainly focuses on solving the multiple objective combinatorial optimization problems. This paper incorporates crowding update technology into MOACOB and proposes a novel crowding based MOACO biclustering algorithm to mine biclusters from microarray dataset. Experimental results are shown for biclustering algorithm on two real gene expression dataset.

In this paper, we present a context-sensitive approach for re-ranking retrieved documents for further improving the effectiveness of high-performance biomedical literature retrieval systems. For each topic, a two-dimensional context is learnt from the top N and the last N' documents in initial retrieval ranked list, which contains lexical context and conceptual context. The probabilities that retrieved documents are generated within the contextual space are then computed for document re-ranking. Empirical evaluation on the TREC Genomics full-text collection and two strong biomedical literature retrieval runs demonstrates that the context-sensitive re-ranking approach yields better retrieval performance.

Combination of multiple evidences has been shown to be effective in genomics literature retrieval. Citation information is an intuitive evidence for facilitating literature retrieval. Previous research on citation analysis has demonstrated that useful linkage information can be extracted from the citation graph. However, the question of how the combination of citation evidence and content evidence should be done to maximize retrieval accuracy still remains largely unanswered. In this paper, we propose BioCLink, a new probabilistic approach that integrates citation evidence into content-based weighting function for improving genomics literature retrieval performance. Based on findings of our previous study, a strategy for modeling citation evidence is proposed. BioCLink provides the combination of content and citation evidences with a theoretical support. Moreover, exhaustiveparameter tuning can be avoided using BioCLink. Extensive experiments on TREC 2006 and 2007 Genomics collections demonstrate the advantages and effectiveness of our proposed methods.

As the first DHT implemented in real applications and involving millions of simultaneous users, all aspects of Kad must be analyzed and measured carefully. This paper focuses on measuring the routing table of Kad in eMule/aMule. We present and analyze the availability and stability of routing table by crawling actively. We find the phenomenon of ID repetition in Kad that many peers use a same ID simultaneously, which will decrease the performance of routing and then reduce the availability of routing table. The connection availability of global routing table is relatively low, the average of which is about 64.9%. Connection availability influences the efficiency of searching and routing in Kad network directly.

We propose an efficient certificateless public key encryption (CL-PKE) scheme which is provably secure against chosen ciphertext attacks without random oracles. Our scheme is more computationally efficient than the existing schemes and provides the shortest public key length compared to other existing CL-PKEs with random oracles. We also propose a practical self-generated-certificate encryption (SGC-PKE) scheme based on our CL-PKE scheme. One of merits of such cryptographic systems is that it can be applied to countermeasure "Denial-of-Decryption (DoD) Attacks" that is inherent in CL-PKE.

ID uniqueness is essential in DHT-based systems as peer lookup and resource searching rely on ID-matching. Many previous works and measurements on Kad do not take into account that IDs among peers may not be unique. We observe that a significant portion of peers, 19.5% of the peers in routing tables and 4.5% of the active peers (those who respond to Kad protocol), do not have unique IDs. These repetitions would mislead the measurements of Kad network. We further observe that there are a large number of peers that frequently change their UDP ports, and there are a few IDs that repeat for a large number of times and all peers with these IDs do not respond to Kad protocol. We analyze the effects of ID repetitions under simplified settings and find that ID repetition degrades Kad's performance on publishing and searching, but has insignificant effect on lookup process. These measurement and analysis are useful in determining the sources of repetitions and are also useful in finding suitable parameters for publishing and searching.

Constructing program invariants is one of the key problems of program verification. A lot of approaches to invariant generation have been reported, and all of these methods assume that program variables are evaluated over infinite domains such as rational or integer. Actually, during the execution of program, all variables are expressed using bit-vectors with limited width and evaluated over finite domains. Many invariants suit for infinite domains may be invalid in finite domains, and vice versa. This paper proposes an approach to construct invariants for program whose variables are evaluated over finite domains. This method translates a program into constraints that are solved using a QBF (Quantified Boolean Formula) solver to yield desired program invariants. It can be used to discover a rich class of invariants including linear (or polynomial) equality (or inequality) invariants involving operations like addition, multiplication, division, shift, bitwise operation, even quantifiers. And we also show how this technique can be used to prove partial correctness, termination and total correctness.

BACKGROUND: High-throughput microarray technologies have generated and accumulated massive amounts of gene expression datasets that contain expression levels of thousands of genes under hundreds of different experimental conditions. The microarray datasets are usually presented in 2D matrices, where rows represent genes and columns represent experimental conditions. The analysis of such datasets can discover local structures composed by sets of genes that show coherent expression patterns under subsets of experimental conditions. It leads to the development of sophisticated algorithms capable of extracting novel and useful knowledge from a biomedical point of view. In the medical domain, these patterns are useful for understanding various diseases, and aid in more accurate diagnosis, prognosis, treatment planning, as well as drug discovery. RESULTS: In this work we present the CMOPSOB (Crowding distance based Multi-objective Particle Swarm Optimization Biclustering), a novel clustering approach for microarray datasets to cluster genes and conditions highly related in sub-portions of the microarray data. The objective of biclustering is to find sub-matrices, i.e. maximal subgroups of genes and subgroups of conditions where the genes exhibit highly correlated activities over a subset of conditions. Since these objectives are mutually conflicting, they become suitable candidates for multi-objective modelling. Our approach CMOPSOB is based on a heuristic search technique, multi-objective particle swarm optimization, which simulates the movements of a flock of birds which aim to find food. In the meantime, the nearest neighbour search strategies based on crowding distance and -dominance can rapidly converge to the Pareto front and guarantee diversity of solutions. We compare the potential of this methodology with other biclustering algorithms by analyzing two common and public datasets of gene expression profiles. In all cases our method can find localized structures related to sets of genes that show consistent expression patterns across subsets of experimental conditions. The mined patterns present a significant biological relevance in terms of related biological processes, components and molecular functions in a species-independent manner. CONCLUSION: The proposed CMOPSOB algorithm is successfully applied to biclustering of microarray dataset. It achieves a good diversity in the obtained Pareto front, and rapid convergence. Therefore, it is a useful tool to analyze large microarray datasets.

With the advent of the DNA microarray technology,it is now possible to study the transcriptional response of a complete genome to different experimental conditions. Biclustering is a very useful data mining technique for analysis of those gene expression data.During biclustering several objectives in conflict with each other have to be optimized simultaneously, so multi-objective modeling is suitable for solving biclustering problem. This paper proposes a novel multi-objective particle swarm optimization biclustering (MOPSOB) algorithm to mine coherent patterns from microarray data. Experimental results on real datasets show that our approach can effectively find significant biclusters of high quality.

Kademlia-based DHT has been deployed in many P2P applications and it is reported that there are millions of simultaneous users in Kad network. For such a protocol that significantly involves so many peers, its robustness and security must be evaluated carefully. In this paper, we analyze the Kademlia protocol and identify several potential vulnerabilities. We classify potential attacks as three types: asymmetric attack, routing table reflection attack and index reflection attack. A limited real-world experiment was run on eMule and the results show that these attacks tie up bandwidth and TCP connection resources of victim. We analyze the results of our experiment in three aspects: the effect of DDoS attacks by misusing Kad in eMule, the comparison between asymmetric attack and routing table reflection attack, and the distribution of attacks. More large-scale DDoS attack can be performed by means of a little more effort. We introduce some methods to amplify the performance of attack and some strategies to evade detection. Finally, we further discuss several solutions for these DDoS attacks.

Recent work has shown that ontology is useful to improve the performance of information retrieval, especially in biomedical literatures. The method of ontology-based can solve synonym problems. In this paper, we propose a new frame for genomic information retrieval based on UMLS. In our frame, genomic information retrieval includes three processes: first, documents were indexed based UMLS, which means documents were represented by concepts, besides, the concept weight was re-calculated combined with similarity between concepts. Second, documents were clustered using fuzzy c-means method. At last cluster language model is utilized for information retrieval. Our method can solve partly synonymy and polysemy problems. The new method is evaluated on TREC 2004/05 genomics track collections. Experiments show that the retrieval performance is greatly improved by the new method compared with the basic language model.

The cubelike recursive networks is a special sub family of the binary interconnection networks. Typical cubelike recursive networks include the hypercube, the crossed cube, the Mobius cube, the generalized twisted cube, the twisted n-cube and the twisted-cube connected network. In a general sense, lots of their topological properties and network parameters are identical, but their diameters are quite different. This work makes the following contributions: Firstly, the definitions of sub-network and super-network are introduced to explain the recursive nature on structure of the cubelike recursive networks. Secondly, the supremum and infimum of the cubelike recursive networks' diameters are n and [~(n +1)/2] respectively, which are proved according to these definitions. Finally, a routing algorithm of cubelike recursive networks is proposed, with an example presented to explain how the algorithm works.