Yubo Shan, Kun Zhang, Qiming Xu, Liping Cao, Yingying Cao, Jian Zhang, Yu Wang, Jingyuan Li, Yuanzhuo Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Tian Xueyun, MingHua Ma, Bingbing Xu, Nuoyan Lyu, Wei Li, Heng Dong, Zheng Chu, Yuanzhuo Wang, Huawei Shen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Inspired by this, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It first treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation, then introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: by leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a SOTA in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.

Zhichao Shi, Shaoling Jing, Yi Cheng, Hao Zhang, Yuanzhuo Wang, Jie Zhang, Huawei Shen, Xueqi Cheng. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Large language models (LLMs) have recently demonstrated remarkable performance across various Natual Language Processing tasks. In the field of multi-hop reasoning, the Chain-of-thought (CoT) prompt method has emerged as a paradigm, using curated stepwise reasoning demonstrations to enhance LLM's ability to reason and produce coherent rational pathways. To ensure the accuracy, reliability, and traceability of the generated answers, many studies have incorporated information retrieval (IR) to provide LLMs with external knowledge. However, existing CoT with IR methods decomposes questions into sub-questions based on a single compositionality type, which limits their effectiveness for questions involving multiple compositionality types. Additionally, these methods suffer from inefficient retrieval, as complex questions often contain abundant information, leading to the retrieval of irrelevant information inconsistent with the query's intent. In this work, we propose a novel question decomposition framework called TRQA for multi-hop question answering, which addresses these limitations. Our framework introduces a reasoning tree (RT) to represent the structure of complex questions. It consists of four components: the Reasoning Tree Constructor (RTC), the Question Generator (QG), the Retrieval and LLM Interaction Module (RAIL), and the Answer Aggregation Module (AAM). Specifically, the RTC predicts diverse sub-question structures to construct the reasoning tree, allowing a more comprehensive representation of complex questions. The QG generates sub-questions for leaf-node in the reasoning tree, and we explore two methods for QG: prompt-based and T5-based approaches. The IR module retrieves documents aligned with sub-questions, while the LLM formulates answers based on the retrieved information. Finally, the AAM aggregates answers along the reason tree, producing a definitive response from bottom to top.

Xuhui Jiang, Yinghan Shen, Zhichao Shi, Chengjin Xu, Wei Li, Zixuan Li, Jian Guo, Huawei Shen, Yuanzhuo Wang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

While auxiliary information has become a key to enhancing Large Language Models (LLMs), relatively little is known about how LLMs merge these contexts, specifically contexts generated by LLMs and those retrieved from external sources.To investigate this, we formulate a systematic framework to identify whether LLMs' responses are attributed to either generated or retrieved contexts.To easily trace the origin of the response, we construct datasets with conflicting contexts, i.e., each question is paired with both generated and retrieved contexts, yet only one of them contains the correct answer.Our experiments reveal a significant bias in several LLMs (GPT-4/3.5 and Llama2) to favor generated contexts, even when they provide incorrect information.We further identify two key factors contributing to this bias: i) contexts generated by LLMs typically show greater similarity to the questions, increasing their likelihood of being selected; ii) the segmentation process used in retrieved contexts disrupts their completeness, thereby hindering their full utilization in LLMs.Our analysis enhances the understanding of how LLMs merge diverse contexts, offers valuable insights for advancing current LLM augmentation methods, and highlights the risk of generated misinformation for retrieval-augmented LLMs 1 .

The questionnaire is a professional research methodology used for both qualitative and quantitative analysis of human opinions, preferences, attitudes, and behaviors. However, designing and evaluating questionnaires demands significant effort due to their intricate and complex structure. Questionnaires entail a series of questions that must conform to intricate constraints involving the questions, options, and overall structure. Specifically, the questions should be relevant and specific to the given research topic and intent. The options should be tailored to the questions, ensuring they are mutually exclusive, completed, and ordered sensibly. Moreover, the sequence of questions should follow a logical order, grouping similar topics together. As a result, automatically generating questionnaires presents a significant challenge and this area has received limited attention primarily due to the scarcity of high-quality datasets. To address these issues, we present Qsnail, the first dataset specifically constructed for the questionnaire generation task, which comprises 13,168 human-written questionnaires gathered from online platforms. We further conduct experiments on Qsnail, and the results reveal that retrieval models and traditional generative models do not fully align with the given research topic and intents. Large language models, while more closely related to the research topic and intents, exhibit significant limitations in terms of diversity and specificity. Despite enhancements through the chain-of-thought prompt and finetuning, questionnaires generated by language models still fall short of human-written questionnaires. Therefore, questionnaire generation is challenging and needs to be further explored. The dataset will be published in the future.

The flourishing of knowledge graph (KG) applications has driven the need for entity alignment (EA) across KGs. However, the heterogeneity of practical KGs, characterized by differing scales, structures, and limited overlapping entities, greatly surpasses that of existing EA datasets. This discrepancy highlights an oversimplified heterogeneity in current EA datasets, which obstructs the exploration of the EA application. In this paper, we study the performance of EA methods on the alignment of highly heterogeneous KGs (HHKGs). Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios. Then, based on these datasets, we conduct extensive experiments to evaluate previous representative EA methods. Our findings reveal that, in aligning HHKGs, valuable structure information can hardly be exploited, which leads to inferior performance of existing EA methods, especially those based on GNNs. These findings shed light on the potential problems associated with the conventional application of GNN-based methods as a panacea for all EA datasets. Consequently, to elucidate what EA methodology is genuinely beneficial in practical scenarios, we undertake an in-depth analysis by implementing a simple but effective approach: Simple-HHEA. Our experiment results conclude that the key to the future EA model design in practice lies in their adaptability and efficiency to varying information quality conditions, as well as their capability to capture patterns across HHKGs. The datasets and source code are available at https://github.com/IDEA-FinAI/Simple-HHEA.

Abstract Entity recognition of product titles is essential for retrieving and recommending product information. Due to the irregularity of product title text, such as informal sentence structure, a large number of professional attribute words, a large number of unrelated independent entities of various combinations, the existing general named entity recognition model is limited in the e‐commerce field of product title entity recognition. Most of the current studies focus on only one of the two challenges instead of considering the two challenges together. Our approach proposes NEZHA‐CNN‐GlobalPointer architecture with the addition of label semantic network, and uses multigranularity contextual and label semantic information to fully capture the internal structure and category information of words and texts to improve the entity recognition accuracy. Through a series of experiments, we proved the efficiency of our approach over a dataset of Chinese product titles from JD.com, improving the F1‐value by 5.98%, when compared to the BERT‐LSTM‐CRF model on the product title corpus.

Legal case retrieval, which aims to find relevant cases based on a short case description, serves as an important part of modern legal systems. Despite the success of existing retrieval methods based on Pretrained Language Models, there are still two issues in legal case retrieval that have not been well considered before. First, existing methods underestimate the semantics associations among legal elements, e.g., law articles and crimes, which played an essential role in legal case retrieval. These methods only adopt the pre-training language model to encode the whole legal case, instead of distinguishing different legal elements in the legal case. They randomly split a legal case into different segments, which may break the completeness of each legal element. Second, due to the difficulty in annotating the relevant labels of similar cases, legal case retrieval inevitably faces the problem of lacking training data. In this paper, we propose a counterfactual graph learning framework for legal case retrieval. Concretely, to overcome the above challenges, we transform the legal case document into a graph and model the semantics of the legal elements through a graph neural network. To alleviate the low resource and learn the causal relationship between the semantics of legal elements and relevance, a counterfactual data generator is designed to augment counterfactual data and enhance legal case representation. Extensive experiments based on two publicly available legal benchmarks demonstrate that our CFGL-LCR can significantly outperform previous state-of-the-art methods in legal case retrieval.

With the overwhelming popularity of Knowledge Graphs (KGs), researchers have poured attention to link prediction to fill in missing facts for a long time. However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity). In practice, n-ary relational facts are also ubiquitous. When encountering such facts, existing studies usually decompose them into triples by introducing a multitude of auxiliary virtual entities and additional triples. These conversions result in the complexity of carrying out link prediction on n-ary relational data. It has even proven that they may cause loss of structure information. To overcome these problems, in this paper, we represent each n-ary relational fact as a set of its role and role-value pairs. We then propose a method called NaLP to conduct link prediction on n-ary relational data, which explicitly models the relatedness of all the role and role-value pairs in an n-ary relational fact. We further extend NaLP by introducing type constraints of roles and role-values without any external type-specific supervision, and proposing a more reasonable negative sampling mechanism. Experimental results validate the effectiveness and merits of the proposed methods.

Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints. Existing methods train one encoder-decoder-based model to fit all questions. However, such a one-size-fits-all strategy may not perform well since complex questions exhibit an uneven distribution in many dimensions, such as question types, involved KB relations, and query structures, resulting in insufficient learning for long-tailed samples under different dimensions. To address this problem, we propose a meta-learning framework for complex question generation. The meta-trained generator can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples through a few most related training samples. To retrieve similar samples for each input query, we design a self-supervised graph retriever to learn distributed representations for samples, and contrastive learning is leveraged to improve the learned representations. We conduct experiments on both WebQuestionsSP and ComplexWebQuestion, and results on long-tailed samples of different dimensions have been significantly improved, which demonstrates the effectiveness of the proposed framework.

Link prediction over a knowledge graph aims to predict the missing head entities$h$or tail entities$t$and missing relations$r$for a triple$(h,r,t)$. Recent years have witnessed great advance of knowledge graph embedding based link prediction methods, which represent entities and relations as elements of a continuous vector space. Most methods learn the embedding vectors by optimizing a margin-based loss function, where the margin is used to separate negative and positive triples in the loss function. The loss function utilizes the general structures of knowledge graphs, e.g., the vector of$r$is the translation of the vector of$h$and$t$, and the vector of$t$should be the nearest neighbor of the vector of$h+r$. However, there are many particular structures, and can be employed to promote the performance of link prediction. One typical structure in knowledge graphs is hierarchical structure, which existing methods have much unexplored. We argue that the hierarchical structures also contain rich inference patterns, and can further enhance the link prediction performance. In this paper, we propose a hierarchy-constrained link prediction method, called hTransM, on the basis of the translation-based knowledge graph embedding methods. It can adaptively determine the optimal margin by detecting the single-step and multi-step hierarchical structures. Moreover, we prove the effectiveness of hTransM theoretically, and experiments over three benchmark datasets and two sub-tasks of link prediction demonstrate the superiority of hTransM.

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng. 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.

Knowledge Graph (KG) reasoning that predicts missing facts for incomplete KGs has been widely explored. However, reasoning over Temporal KG (TKG) that predicts facts in the future is still far from resolved. The key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps, where all concurrent facts in each KG exhibit structural dependencies and temporally adjacent facts carry informative sequential patterns. To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently. Specifically, for the evolution unit, a relation-aware GCN is leveraged to capture the structural dependencies within the KG at each timestamp. In order to capture the sequential patterns of all facts in parallel, the historical KG sequence is modeled auto-regressively by the gate recurrent components. Moreover, the static properties of entities, such as entity types, are also incorporated via a static graph constraint component to obtain better entity representations. Fact prediction at future timestamps can then be realized based on the evolutional entity and relation representations. Extensive experiments demonstrate that the RE-GCN model obtains substantial performance and efficiency improvement for the temporal reasoning tasks on six benchmark datasets. Especially, it achieves up to 11.46% improvement in MRR for entity prediction with up to 82 times speedup compared to the state-of-the-art baseline.

Link prediction in knowledge graphs (KGs) aims at predicting potential links between entities in KGs. Existing knowledge graph embedding (KGE) based methods represent individual entities and links in KGs as vectors in low-dimension space. However, these methods focus mainly on the link prediction of individual entities, yet neglect that between group entities, which exist widely in real-world KGs. In this paper, we propose a KGE based method, called GTransA, for link prediction between group entities in a heterogeneous network by integrating individual entity links into group entity links during prediction. Experiments show that GTransA decreases mean rank by 5.4%, compared to TransA.

Knowledge inference on knowledge graph has attracted extensive attention, which aims to find out connotative valid facts in knowledge graph and is very helpful for improving the performance of many downstream applications.However, researchers have mainly poured attention to knowledge inference on binary facts.The studies on n-ary facts are relatively scarcer, although they are also ubiquitous in the real world.Therefore, this paper addresses knowledge inference on n-ary facts.We represent each n-ary fact as a primary triple coupled with a set of its auxiliary descriptive attribute-value pair(s).We further propose a neural network model, NeuInfer, for knowledge inference on n-ary facts.Besides handling the common task to infer an unknown element in a whole fact, NeuInfer can cope with a new type of task, flexible knowledge inference.It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s).Experimental results demonstrate the remarkable superiority of NeuInfer.

Knowledge Graph Question Answering aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge graphs. When faced with a complex question with compositional semantics, query graph generation is a practical semantic parsing-based method. But existing works rely on heuristic rules with limited coverage, making them impractical on more complex questions. This paper proposes a Director-Actor-Critic framework to overcome these challenges. Through options over a Markov Decision Process, query graph generation is formulated as a hierarchical decision problem. The Director determines which types of triples the query graph needs, the Actor generates corresponding triples by choosing nodes and edges, and the Critic calculates the semantic similarity between the generated triples and the given questions. Moreover, to train from weak supervision, we base the framework on hierarchical Reinforcement Learning with intrinsic motivation. To accelerate the training process, we pre-train the Critic with high-reward trajectories generated by hand-crafted rules, and leverage curriculum learning to gradually increase the complexity of questions during query graph generation. Extensive experiments conducted over widely-used benchmark datasets demonstrate the effectiveness of the proposed framework.

Knowledge Graph Question Answering aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge graphs. When faced with a multi-relation question, existing embedding-based approaches take the whole topic-entity-centric subgraph into account, resulting in high time complexity. Meanwhile, due to the high cost for data annotations, it is impractical to exactly show how to answer a complex question step by step, and only the final answer is labeled, as weak supervision. To address these challenges, this paper proposes a neural method based on reinforcement learning, namely Stepwise Reasoning Network, which formulates multi-relation question answering as a sequential decision problem. The proposed model performs effective path search over the knowledge graph to obtain the answer, and leverages beam search to reduce the number of candidates significantly. Meanwhile, based on the attention mechanism and neural networks, the policy network can enhance the unique impact of different parts of a given question over triple selection. Moreover, to alleviate the delayed and sparse reward problem caused by weak supervision, we propose a potential-based reward shaping strategy, which can accelerate the convergence of the training algorithm and help the model perform better. Extensive experiments conducted over three benchmark datasets well demonstrate the effectiveness of the proposed model, which outperforms the state-of-the-art approaches.

Knowledge graphs have recently been extensively applied in many different areas (e.g., disaster management and relief, disease diagnosis). For example, event-centric knowledge graphs have been developed to improve decision making in disaster management and relief. This paper focuses on the task of event detection, which is the precondition of event extraction for constructing event-centric knowledge graphs. Event detection identifies trigger words of events in the sentences of a document and further classifies the types of events. It is straightforward that context information is useful for event detection. Therefore, the feature-based methods adopt cross-sentence information. However, they suffer from the complication of human-designed features. On the other hand, the representation-based methods learn document-level embeddings, which, however, contain much noise caused by unsupervised learning. To overcome these problems, in this paper we propose a new model based on Semi-supervised Auto-Encoder, which learns Context information to Enhance Event Detection, thus called SAE-CEED. This model first applies large-scale unlabeled texts to pre-train an auto-encoder, so that the embeddings of segments learned by the encoder contain the semantic and order information of the original text. It then uses the decoder to extract the context embeddings and fine-tunes them to enhance a bidirectional neural network model to identify event triggers and their types in sentences. Through experiments on the benchmark ACE-2005 dataset, we demonstrate the effectiveness of the proposed SAE-CEED model. In addition, we systematically conduct a series of experiments to verify the impact of different lengths of text segments in the pre-training of the auto-encoder on event detection.

With the overwhelming popularity of Knowledge Graphs (KGs), researchers have poured attention to link prediction to complete KGs for a long time. However, they mainly focus on promoting the performance on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity). In practice, n-ary relational facts are also ubiquitous. When encountering such facts, existing studies usually decompose them into triples by introducing a multitude of auxiliary virtual entities and additional triples. These conversions result in the complexity of carrying out link prediction concerning more than two arities. It has even proven that they may cause loss of structural information. To overcome these problems, in this paper, without decomposition, we represent each n-ary relational fact as a set of its role-value pairs. We further propose a method to conduct Link Prediction on N-ary relational data, thus called NaLP, which explicitly models the relatedness of all the role-value pairs in the same n-ary relational fact. Experimental results validate the effectiveness and merits of the proposed NaLP method.

Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure. It suffers from the label noise in training data generated by distant supervision. Although recent studies use many features to prune wrong label ahead of training, they suffer from error propagation and bring much complexity. In this paper, we propose an end-to-end typing model, called the path-based attention neural model (PAN), to learn a noise-robust performance by leveraging the hierarchical structure of types. Experiments on two data sets demonstrate its effectiveness.

Knowledge Graphs (KGs) have facilitated many real-world applications (e.g., vertical search and intelligent question answering). However, they are usually incomplete, which affects the performance of such KG based applications. To alleviate this problem, a number of Knowledge Graph Completion (KGC) methods have been developed to predict those implicit triples. Tensor/matrix based methods and translation based methods have attracted great attention for a long time. Recently, neural network has been introduced into KGC due to its extensive superiority in many fields (e.g., natural language processing and computer vision), and achieves promising results. In this paper, we propose a Shared Embedding based Neural Network (SENN) model for KGC. It integrates the prediction tasks of head entities, relations and tail entities into a neural network based framework with shared embeddings of entities and relations, while explicitly considering the differences among these prediction tasks. Moreover, we propose an adaptively weighted loss mechanism, which dynamically adjusts the weights of losses according to the mapping properties of relations, and the prediction tasks. Since relation prediction usually performs better than head and tail entity predictions, we further extend SENN to SENN+ by employing it to assist head and tail entity predictions. Experiments on benchmark datasets validate the effectiveness and merits of the proposed SENN and SENN+ methods. The shared embeddings and the adaptively weighted loss mechanism are also testified to be effective.

Information selection is the most important component in document summarization task.In this paper, we propose to extend the basic neural encoding-decoding framework with an information selection layer to explicitly model and optimize the information selection process in abstractive document summarization.Specifically, our information selection layer consists of two parts: gated global information filtering and local sentence selection.Unnecessary information in the original document is first globally filtered, then salient sentences are selected locally while generating each summary sentence sequentially.To optimize the information selection process directly, distantly-supervised training guided by the golden summary is also imported.Experimental results demonstrate that the explicit modeling and optimizing of the information selection process improves document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperform state-of-the-art neural abstractive methods.

Recent neural sequence-to-sequence models have shown significant progress on short text summarization.However, for document summarization, they fail to capture the longterm structure of both documents and multisentence summaries, resulting in information loss and repetitions.In this paper, we propose to leverage the structural information of both documents and multi-sentence summaries to improve the document summarization performance.Specifically, we import both structural-compression and structuralcoverage regularization into the summarization process in order to capture the information compression and information coverage properties, which are the two most important structural properties of document summarization.Experimental results demonstrate that the structural regularization improves the document summarization performance significantly, which enables our model to generate more informative and concise summaries, and thus significantly outperforms state-of-the-art neural abstractive methods.

A knowledge graph is a graph with entities of different types as nodes and various relations among them as edges. The construction of knowledge graphs in the past decades facilitates many applications, such as link prediction, web search analysis, question answering, and so on. Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, for example, TransE, TransH, and TransR, learn the embedding representation by defining a global margin-based loss function over the data. However, the loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidates, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this article, a locally adaptive translation method for knowledge graph embedding, called TransA, is proposed to find the loss function by adaptively determining its margin over different knowledge graphs. Then the convergence of TransA is verified from the aspect of its uniform stability. To make the embedding methods up-to-date when new vertices and edges are added into the knowledge graph, the incremental algorithm for TransA, called iTransA, is proposed by adaptively adjusting the optimal margin over time. Experiments on four benchmark data sets demonstrate the superiority of the proposed method, as compared to the state-of-the-art ones.

Knowledge graph embedding aims to embed entities and relations of knowledge graphs into low-dimensional vector spaces. Translating embedding methods regard relations as the translation from head entities to tail entities, which achieve the state-of-the-art results among knowledge graph embedding methods. However, a major limitation of these methods is the time consuming training process, which may take several days or even weeks for large knowledge graphs, and result in great difficulty in practical applications. In this paper, we propose an efficient parallel framework for translating embedding methods, called ParTrans-X, which enables the methods to be paralleled without locks by utilizing the distinguished structures of knowledge graphs. Experiments on two datasets with three typical translating embedding methods, i.e., TransE [3], TransH [19], and a more efficient variant TransE- AdaGrad [11] validate that ParTrans-X can speed up the training process by more than an order of magnitude.

Link inference, i.e., inferring links between vertices in a heterogeneous information network with heterogeneous vertices and edges, has been extensively studied in recent years. So far, many machine learning-based methods have been proposed for link inference, which can be classified into two categories, namely, supervised and unsupervised. Supervised methods perform well but highly rely on feature selection and training data. Although unsupervised methods are inferior to supervised ones, they work in a relatively simple way without considering the class distribution of the training data. In this paper, we investigate the link inference problem in heterogeneous information networks by proposing a knapsack-constrained inference method. Specifically, we integrate dynamic information into the heterogeneous information network and further formalize the link inference problem as a knapsack-like problem. We then solve it by the virtue of a 0-1 knapsack analogous optimization approach and investigate the time complexity of the proposed approach. Finally, experimental results show that the proposed unsupervised method can obtain high performance comparable to supervised method for some cases.

Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, e.g., TransE and TransH, learn embedding representation by defining a global margin-based loss function over the data. However, the optimal loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidate loss functions, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this paper, we propose a locally adaptive translation method for knowledge graph embedding, called TransA, to find the optimal loss function by adaptively determining its margin over different knowledge graphs. Experiments on two benchmark data sets demonstrate the superiority of the proposed method, as compared to the-state-of-the-art ones.

Predicting links and their building time in a knowledge network has been extensively studied in recent years. Most structure-based predictive methods consider structures and the time information of edges separately, which fail to characterize the correlation between them. In this paper, we propose a structure called the Time-Difference-Labeled Path, and a link prediction method (TDLP). Experiments show that TDLP outperforms the state-of-the-art methods.

Sentiment classification aims to determine the sentiment polarity expressed in a text. In online customer reviews, the sentiment polarities of words are usually dependent on the corresponding aspects. For instance, in mobile phone reviews, we may expect the long battery time but not enjoy the long response time of the operating system. Therefore, it is necessary and appealing to consider aspects when conducting sentiment classification. Probabilistic topic models that jointly detect aspects and sentiments have gained much success recently. However, most of the existing models are designed to work well in a language with rich resources. Directly applying those models on poor-quality corpora often leads to poor results. Consequently, a potential solution is to use the cross-lingual topic model to improve the sentiment classification for a target language by leveraging data and knowledge from a source language. However, the existing cross-lingual topic models are not suitable for sentiment classification because sentiment factors are not considered therein. To solve these problems, we propose for the first time a novel cross-lingual topic model framework which can be easily combined with the state-of-the-art aspect/sentiment models. Extensive experiments in different domains and multiple languages demonstrate that our model can significantly improve the accuracy of sentiment classification in the target language.

In social networks, predicting a user’s location mainly depends on those of his/her friends, where the key lies in how to select his/her most influential friends. In this article, we analyze the theoretically maximal accuracy of location prediction based on friends’ locations and compare it with the practical accuracy obtained by the state-of-the-art location prediction methods. Upon observing a big gap between the theoretical and practical accuracy, we propose a new strategy for selecting influential friends in order to improve the practical location prediction accuracy. Specifically, several features are defined to measure the influence of the friends on a user’s location, based on which we put forth a sequential random-walk-with-restart procedure to rank the friends of the user in terms of their influence. By dynamically selecting the top N most influential friends of the user per time slice, we develop a temporal-spatial Bayesian model to characterize the dynamics of friends’ influence for location prediction. Finally, extensive experimental results on datasets of real social networks demonstrate that the proposed influential friend selection method and temporal-spatial Bayesian model can significantly improve the accuracy of location prediction.

Privacy theft malware has become a serious and challenging problem to cyber security. Previous methods are of different categories: one focuses on the outbound network traffic and the other one dives into the inside information flow of the program. We incorporate dynamic behavior analysis with network traffic analysis and present an abstract model called Privacy Petri Net PPN, which is more applicable to various kinds of malware and more understandable to users. In consideration of the multi-process technique adopted by new malware, we also model the collaborative behaviors between different malicious functionality modules with PPN. We apply our approach to real-world malware, and the experiment result shows that our approach can effectively find categories, content, source, and destination of the privacy theft behavior of the malware sample. Copyright © 2013 John Wiley & Sons, Ltd.

Due to the development of web services, many social network sites, as well as online shopping sites have been booming in the past decade, where it is a common phenomenon that people are likely to use multiple services at the same time. On the one hand, previous research findings indicate the data sparsity issues of online shopping accounts, which is caused by the heavy-tailed distribution of user information. On the other hand, in social network sites, the personal information and the corresponding statuses of an account are abundant, and their genuineness is guaranteed either by the service provider, or by the willingness of the account owner to connect to his or her friends in reality. Making use of the correlation between accounts of a same individual is a crucial prerequisite for many interesting cross network applications, such as improving the recommendation performance of the online shopping sites using extra information from social network services. In this paper, we firstly propose a game-theoretic method to identify correlation accounts of individuals between social network sites and online shopping sites with stable matching model, incorporating account profiles as well as historical behaviors. Using the above account relationships, we then put forward a predicting method that combines heterogeneous social network information and online shopping information, to predict the purchasing behaviors. The results show that our method identifies up to 70 % of the correlation accounts between Facebook and eBay, one of the most popular social network sites and online shopping sites in the world, respectively. The experimental results also show that using the correlation account sets, the accuracy of our purchase predicting method outperforms the state-of-the-art methods by 5 %.

One challenge of link prediction in online social networks is the large scale of many such networks. The measures used by existing work lack a computational consideration in the large scale setting. We propose the notion of social distance in a multi-dimensional form to measure the closeness among a group of people in Microblogs. We proposed a fast hashing approach called Locality-sensitive Social Distance Hashing (LSDH), which works in an unsupervised setup and performs approximate near neighbor search without high-dimensional distance computation. Experiments were applied over a Twitter dataset and the preliminary results testified the effectiveness of LSDH in predicting the likelihood of future associations between people.

Relation inference between concepts in knowledge base has been extensively studied in recent years. Previous methods mostly apply the relations in the knowledge base, without fully utilizing the contents, i.e., the attributes of concepts in knowledge base. In this paper, we propose a content-structural relation inference method (CSRI) which integrates the content and structural information between concepts for relation inference. Experiments on data sets show that CSRI obtains 15% improvement compared with the state-of-the-art methods.

With the coming of the era of big data, it is most urgent to establish the knowledge computational engine for the purpose of discovering implicit and valuable knowledge from the huge, rapidly dynamic, and complex network data. In this paper, we first survey the mainstream knowledge computational engines from four aspects and point out their deficiency. To cover these shortages, we propose the open knowledge network (OpenKN), which is a self-adaptive and evolutionable knowledge computational engine for network big data. To the best of our knowledge, this is the first work of designing the end-to-end and holistic knowledge processing pipeline in regard with the network big data. Moreover, to capture the evolutionable computing capability of OpenKN, we present the evolutionable knowledge network for knowledge representation. A case study demonstrates the effectiveness of the evolutionable computing of OpenKN.

Populating a knowledge base with new entity mentions extracted from unstructured text can help enhance its coverage and freshness. It naturally consists of two subtasks, namely, fine-grained entity classification and entity linking. Existing studies often focus on one of these two subtasks and they usually populate entity mentions in the same text by implicitly assuming that they are independent. However, these entity mentions are often semantically related to each other and it would be better to populate them into the knowledge base collectively. For solving these problems, in this paper we propose an interdependence graph based and unified collective inference approach, called CIIGA, to populating a knowledge base with collective entities, which can jointly determine the proper locations of all entity mentions in the same text by exploiting their interdependence relationships. Experimental results show that this approach can achieve significant accuracy improvement, as compared to the baseline approach, APOLLO, on the task of knowledge base population with multiple entities.

Sentiment analysis in various languages has been a research hotspot with many applications. However, sentiment resources (e.g., labeled corpora, sentiment lexicons) of different languages are unbalanced in terms of quality and quantity, which arouses interests in cross-lingual sentiment analysis aiming at using the resources in a source language to improve sentiment analysis in a target language. Nevertheless, many existing cross-lingual related works rely on a certain machine translation system to directly adapt the labeled data from the source language to the target language, which usually suffers from inaccurate results generated by the machine translation system. On the other hand, most sentiment analysis studies focus on document-level sentiment classification that cannot solve the aspect dependency problem of sentiment words. For instance, in the reviews on a cell phone, long is positive for the lifespan of its battery, but negative for the response time of its operating system. To solve these problems, this paper develops a novel Cross-Lingual Joint Aspect/Sentiment (CLJAS) model to carry out aspect-specific sentiment analysis in a target language using the knowledge learned from a source language. Specifically, the CLJAS model jointly detects aspects and sentiments of two languages simultaneously by incorporating sentiments into a cross-lingual topic model framework. Extensive experiments on different domains and different languages demonstrate that the proposed model can significantly improve the accuracy of sentiment classification in the target language.

Information dissemination of emergency events can be considered quickly proliferate over social network, the basic fact is a complex course of interactions of numerous participants. In this paper, we first analyze the information features of emergency events in social network. Then propose users' utility to describe the effect and present a stochastic game for the information interaction between users in social network has. Finally, a case to observe the information dissemination of emergency events is presented to show that users with different personality have different dissemination scale in social network.

Social tagging has grown in popularity on the web due to its effectiveness in organizing and accessing web pages. This short paper addresses the problem of automated social tagging, which aims to predict tags for web pages automatically and help with future navigation, filtering or search. We explore and find three foundations of the collaborative tags in social tagging services, that are consistency, sharability and stability. The complementary advantages are studied among three well-known methods, i.e. TF-weighted keyword extraction, collaborative filtering approach, and Corr-LDA (correspondence latent Dirichlet allocation) topic model. We then propose a blending model for automated social tagging to emphasize all the foundations, which linearly combines those tags generated by the three methods, and a permutation probability model is built to learn the linear blending. With the experiments on 50,000 training and 10,000 testing web pages from Delicious database, the results show that our blending method outperforms the four baselines. Furthermore, compared with both topic models, Corr-LDA and mixed membership LDA, our approach results in 14.2% and 25.6% of NDCG10improvement separately.

ABSTRACT In this paper, we propose a novel modeling method attack–defense stochastic game Petri nets (or ADSGN) to model and analyze the security issues in enterprise network. We firstly give the definition and modeling method algorithm of ADSGN and then propose the algorithm of the strategy. The proposed ADSGN method is successfully applied to describe the attack and defense courses in the enterprise network. Finally, we analyze the mean time to first security breach and the mean time to security breach in the enterprise network quantifiably, and proved that our method can also be applied to other areas with respect to game issues. Copyright © 2012 John Wiley & Sons, Ltd.

Private information leak has been discovered in many applications and has become serious and challenging problem to cyber security. Previous works are based on two categories of road map, the one focuses on the outbound network traffic of application, the other one dives into the inside information flow of application. We incorporate application dynamic behavior analysis with network traffic analysis and present abstract model called Privacy Petri Net (PPN) which is more applicable to various applications and more meaningful to users. We apply our approach on both real world regular application and malware. The experiment result shows that our approach can effectively find categories, content, source and destination of the private information leaks for the target application.

Privacy theft malware has become serious and challenging problem to cyber security. Previous works are based on two categories of road map, the one focuses on the outbound network traffic, the other one dives into the inside information flow. We incorporate dynamic behavior analysis with network traffic analysis and present abstract model called Privacy Petri Net (PPN) which is more applicable to various kinds of malware and more meaningful to users. We apply our approach on real world malware and the experiment result shows that our approach can effectively find categories, content, source and destination of the privacy theft behavior of the malware sample.

Trojan's attack behavior has become increasingly common and diversifiable. How to judge Trojan-like features of the softwares which the users download has become the problem that the users concern about. In this paper, we first capture the software's behavior and related parameters from our virtual software test bed, then a modeling method using Stochastic Petri Nets is proposed, which supports quantitative analysis for the application software's behaviors. Based on the model, the similarity degree between application software and Trojan software is analyzed quantitatively. This analysis show that the model can be used to design an effective anti-Trojan system. The paper concludes with an example to illustrate the effectiveness of the model and analysis method.

DNS has been suffering from cache poisoning attack for a long time. The attacker sends camouflaged DNS response to trick the domain name server, and inserts malicious resource record into the cached database. Because the original DNS protocol only depends on 16-bit transaction ID to verify the response packet, it is prone to be guessed by the attacker. Although many strategies such as transaction randomizing, source port randomizing and the 0×20 technique have been applied to improve the resistance of DNS, the attacker still has chance to poison DNS server in an acceptable time. Other more complicated strategy such as DNSSEC which provides stricter prevention mechanism is not easy to deploy and is not widely adopted yet. To address the problem, we present a novel strategy called Security Proxy. The architecture can be easily implemented and deployed on existing DNS server without modification of DNS server itself. The embedded two schemes Selective Re-Query and Security Label Communication can cooperate and effectively prevent the cache poisoning attack. We analyze our strategy from both the capability and efficiency. Then we find that our Security Proxy has obvious advantage over the original transaction ID, the source port randomizing and 0×20 techniques.

In this paper, we propose a model of email worm propagation based on a novel modeling method, Stochastic Game Nets (SGN), and use this model to analyze the rampant propagation issues of email worm. Combination the conceptual framework of SGN with the practical problems, we get some remarks based on the definitions of SGN in order to precisely describe the details of email worm propagation. An algorithm for solving the equilibrium strategy is presented to calculate the model of SGN. Finally we analyze our research result with several figures, such as infection rate and average propagation time. The results of our work can also offer some references for email users to defend email worms.

This paper concentrates on the performance analysis of channel contention in wireless ad hoc networks by using Stochastic Game Nets (SGN). We refine the definition of SGN so that it can be used to precisely capture the underlying details of a given system. A SGN model is developed to evaluate the channel utilization in a two-node wireless system. We quantify the system performance under equilibrium strategies. The findings of this paper are instructive for the design and deployment of wireless ad hoc networks.

Seamless handover is one of the most attractive research fields in B3G systems. Many mechanisms are proposed to provide certain QoS guarantees in handovers of mobile systems, which would also introduce new threats, such as DoS and DDOS attacks. In this paper, we extend a cookie-based scheme to protect systems from DoS and DDoS attacks. We also adopt a novel queuing network model to analyze our scheme by estimating two essential metrics, i.e. the mean total response time and the mean queue length of MAP. Numerical results indicate that our mechanism works better than the traditional cookie-based scheme and it could effectively help networks defend against abnormal attacks in the handover process.

In this paper, we propose hierarchical Stochastic Game Nets, and use it to model and analyze the security issues in online banking system. Firstly, the definition and modeling algorithm of hierarchical Stochastic Game Nets are given. In which, some theorems are proved. Then we apply hierarchical Stochastic Game Nets to describe the attack and defense course in the online banking. Finally we analyze the attack time and attack probability in the online banking quantitatively based on the model successfully.

The peer-to-peer (P2P) live video streaming system has been demonstrated to have great potential in the public Internet; the large-scale deployment of such systems, however, critically relies on how effective they can deal with the high dynamics encountered, in particular during flash crowd. The rationale behind is that the scaling in P2P live video streaming systems is heavily determined by the timing requirement that streaming applications demand. In this paper, we present an analytical and experimental study on the inherent relationship between the time constraint and the system scale. We develop a generic model for P2P live video streaming that focuses on the peer joining process during flash crowd. We first illustrate that the simple notion of "demand vs. supply" model is insufficient in describing the system scale. By computing the peer start-up time distribution, we demonstrate that the scale is affected by several key factors, especially the peer uploading capacity and the initial system size. We further show the scale is essentially bounded by the timing requirement and the system's capability to accommodate flash crowd is subject to a maximum limit.

In this paper, we propose a novel modeling method, Stochastic Game Nets (SGN), and use it to model and analyze the security issues in enterprise networks. Firstly, the definition and modeling algorithm of Stochastic Game Nets are given. And then we apply the Stochastic Game Nets method to describe the attack and defense course in the enterprise networks successfully, and find a Nash equilibrium. Finally we analyze the confidentiality and integrity of the enterprise network quantificationally based on the model. The method can also be applied to other areas with respect to a game.

To weaken the selfish behavior of nodes in mobile ad hoc networks, many payment-based incentive schemes have been proposed recently, yet it is still far from achieving the expected efficiency to encourage node cooperation. In these schemes, source node selects a Least Cost Routing (LCP) for data transmission according to the forwarding cost reported by intermediate nodes and rewards them with some virtual money before or after successful packet forwarding. However, as a result of information asymmetry between source and relay nodes, nodes on LCP may degrade their efforts promised in the previous routing discovery stage if there is no enough motivation for them to work hard, which exercises a negative influence on the forwarding efficiency of LCP schemes. Therefore, the actual transmission efforts of intermediate nodes must be considered by the source node in the processes of route selecting and packet forwarding. In this paper, with adoption of principal-agent theory of economics, we propose a novel LCP scheme (ELCP) based on the intermediate nodes' effort to stimulate nodes cooperation, in which both source and relay nodes can maximize their profits and ensure routing efficiency simultaneously.

The traditional TCP congestion control is inefficient for high speed networks and it is a challenge to design a high speed replacement for TCP. By simulating some existing high speed protocols, we find that these high speed protocols have limitations in convergence and stability. To address these problems, we apply a population ecology model to design a novel congestion control algorithm-Coupling Logistic TCP(CLTCP). It is based on bandwidth pre-assignment that is similar to XCP and MaxNet. The pre-assignment rate factor is computed in the routers based on the information of the router capacity, the aggregate incoming traffic and the queue length. Then the senders adjust the sending rate according to the pre-assignment rate factor which carries by the packet to strengthen the convergence and stability of transport protocol. The theoretical analysis and simulation results show that CLTCP provides not only fast convergence and strong stability, but also high utilization and fair bandwidth allocation regardless of round trip time.