Personalization, while extensively studied in conventional autonomous driving pipelines, has been largely overlooked in the context of end-to-end autonomous driving (E2EAD), despite its critical role in fostering user trust, safety perception, and real-world adoption. A primary bottleneck is the absence of large-scale real-world datasets that systematically capture driving preferences, severely limiting the development and evaluation of personalized E2EAD models. In this work, we introduce the first large-scale real-world dataset explicitly curated for personalized E2EAD, integrating comprehensive scene topology with rich dynamic context derived from agent dynamics and semantics inferred via a fine-tuned vision-language model (VLM). We propose a hybrid annotation pipeline that combines behavioral analysis, rule-and-distribution-based heuristics, and subjective semantic modeling guided by VLM reasoning, with final refinement through human-in-the-loop verification. Building upon this dataset, we introduce the first standardized benchmark for systematically evaluating personalized E2EAD models. Empirical evaluations on state-of-the-art architectures demonstrate that incorporating personalized driving preferences significantly improves behavioral alignment with human demonstrations.

Recent advances in large language models (LLMs) like ChatGPT have shed light on the development of knowledgeable and versatile AI research assistants in various scientific domains. However, they fall short in biomedical applications due to a lack of proprietary biomedical knowledge and deficiencies in handling biological sequences for molecules and proteins. To address these issues, we present BioMedGPT, a multimodal large language model for assisting biomedical research. We first incorporate domain expertise into LLMs by incremental pre-training on large-scale biomedical literature. Then, we harmonize 2D molecular graphs, protein sequences, and natural language within a unified, parameter-efficient fusion architecture by fine-tuning on multimodal question-answering datasets. Through comprehensive experiments, we show that BioMedGPT performs on par with human experts in comprehending biomedical documents and answering research questions. It also exhibits promising capability in analyzing intricate functions and properties of novel molecules and proteins, surpassing state-of-the-art LLMs by 17.1% and 49.8% absolute gains respectively in ROUGE-L on molecule and protein question-answering.

Cooperatively utilizing both ego-vehicle and infrastructure sensor data via V2X communication has emerged as a promising approach for advanced autonomous driving. However, current research mainly focuses on improving individual modules, rather than taking end-to-end learning to optimize final planning performance, resulting in underutilized data potential. In this paper, we introduce UniV2X, a pioneering cooperative autonomous driving framework that seamlessly integrates all key driving modules across diverse views into a unified network. We propose a sparse-dense hybrid data transmission and fusion mechanism for effective vehicle-infrastructure cooperation, offering three advantages: 1) Effective for simultaneously enhancing agent perception, online mapping, and occupancy prediction, ultimately improving planning performance. 2) Transmission-friendly for practical and limited communication conditions. 3) Reliable data fusion with interpretability of this hybrid data. We implement UniV2X, as well as reproducing several benchmark methods, on the challenging DAIR-V2X, the real-world cooperative driving dataset. Experimental results demonstrate the effectiveness of UniV2X in significantly enhancing planning performance, as well as all intermediate output performance.

Cooperative perception aims to address the inherent limitations of single-vehicle autonomous driving systems through information exchange among multiple agents. Previous research has primarily focused on single-frame perception tasks. However, the more challenging cooperative sequential perception tasks, such as cooperative 3D multi-object tracking, have not been thoroughly investigated. Therefore, we propose CoopTrack, a fully instance-level end-to-end framework for cooperative tracking, featuring learnable instance association, which fundamentally differs from existing approaches. CoopTrack transmits sparse instance-level features that significantly enhance perception capabilities while maintaining low transmission costs. Furthermore, the framework comprises two key components: Multi-Dimensional Feature Extraction, and Cross-Agent Association and Aggregation, which collectively enable comprehensive instance representation with semantic and motion features, and adaptive cross-agent association and fusion based on a feature graph. Experiments on both the V2X-Seq and Griffin datasets demonstrate that CoopTrack achieves excellent performance. Specifically, it attains state-of-the-art results on V2X-Seq, with 39.0\% mAP and 32.8\% AMOTA. The project is available at https://github.com/zhongjiaru/CoopTrack.

Spatial Transcriptomics (ST) technologies provide biologists with rich insights into single-cell biology by preserving spatial context of cells. Building foundational models for ST can significantly enhance the analysis of vast and complex data sources, unlocking new perspectives on the intricacies of biological tissues. However, modeling ST data is inherently challenging due to the need to extract multi-scale information from tissue slices containing vast numbers of cells. This process requires integrating macro-scale tissue morphology, micro-scale cellular microenvironment, and gene-scale gene expression profile. To address this challenge, we propose **SToFM**, a multi-scale **S**patial **T**ranscript**o**mics **F**oundation **M**odel. SToFM first performs multi-scale information extraction on each ST slice, to construct a set of ST sub-slices that aggregate macro-, micro- and gene-scale information. Then an SE(2) Transformer is used to obtain high-quality cell representations from the sub-slices. Additionally, we construct **SToCorpus-88M**, the largest high-resolution spatial transcriptomics corpus for pretraining. SToFM achieves outstanding performance on a variety of downstream tasks, such as tissue region semantic segmentation and cell type annotation, demonstrating its comprehensive understanding of ST data through capturing and integrating multi-scale information.

The value of roadside perception, which could extend the boundaries of autonomous driving and traffic management, has gradually become more prominent and acknowledged in recent years. However, existing roadside perception approaches only focus on the single-infrastructure sensor system, which cannot realize a comprehensive understanding of a traffic area because of the limited sensing range and blind spots. Orienting high-quality roadside perception, we need Roadside Cooperative Perception (RCooper) to achieve practical area-coverage roadside perception for restricted traffic areas. Rcooper has its own domain-specific challenges, but further exploration is hindered due to the lack of datasets. We hence release the first real-world, large-scale RCooper dataset to bloom the research on practical roadside cooperative perception, including detection and tracking. The manually annotated dataset comprises 50k images and 30k point clouds, including two representative traffic scenes (i.e., intersection and corridor). The constructed benchmarks prove the effectiveness of roadside cooperation perception and demonstrate the direction of further research. Codes and dataset can be accessed at: https://github.com/AIR-THU/DAIR-RCooper.

3D molecular representation learning has gained tremendous interest and achieved promising performance in various downstream tasks. A series of recent approaches follow a prevalent framework: an encoder-only model coupled with a coordinate denoising objective. However, through a series of analytical experiments, we prove that the encoder-only model with coordinate denoising objective exhibits inconsistency between pre-training and downstream objectives, as well as issues with disrupted atomic identifiers. To address these two issues, we propose Mol-AE for molecular representation learning, an auto-encoder model using positional encoding as atomic identifiers. We also propose a new training objective named 3D Cloze Test to make the model learn better atom spatial relationships from real molecular substructures. Empirical results demonstrate that Mol-AE achieves a large margin performance gain compared to the current state-of-the-art 3D molecular modeling approach.

Cell identity encompasses various semantic aspects of a cell, including cell type, pathway information, disease information, and more, which are essential for biologists to gain insights into its biological characteristics. Understanding cell identity from the transcriptomic data, such as annotating cell types, has become an important task in bioinformatics. As these semantic aspects are determined by human experts, it is impossible for AI models to effectively carry out cell identity understanding tasks without the supervision signals provided by single-cell and label pairs. The single-cell pre-trained language models (PLMs) currently used for this task are trained only on a single modality, transcriptomics data, lack an understanding of cell identity knowledge. As a result, they have to be fine-tuned for downstream tasks and struggle when lacking labeled data with the desired semantic labels. To address this issue, we propose an innovative solution by constructing a unified representation of single-cell data and natural language during the pre-training phase, allowing the model to directly incorporate insights related to cell identity. More specifically, we introduce **LangCell**, the first **Lang**uage-**Cell** pre-training framework. LangCell utilizes texts enriched with cell identity information to gain a profound comprehension of cross-modal knowledge. Results from experiments conducted on different benchmarks show that LangCell is the only single-cell PLM that can work effectively in zero-shot cell identity understanding scenarios, and also significantly outperforms existing models in few-shot and fine-tuning cell identity understanding scenarios.

Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pre-training on multi-scale code-switch protein sequences and utilizing a multi-scale position encoding to capture relationships among residues and atoms. Experimental results indicate that ESM-AA surpasses previous methods in protein-molecule tasks, demonstrating the full utilization of protein language models. Further investigations reveal that through unified molecular modeling, ESM-AA not only gains molecular knowledge but also retains its understanding of proteins.

Cooperative perception can effectively enhance individual perception performance by providing additional viewpoint and expanding the sensing field. Existing cooperation paradigms are either interpretable (result cooperation) or flexible (feature cooperation). In this paper, we propose the concept of query cooperation to enable interpretable instance-level flexible feature interaction. To specifically explain the concept, we propose a cooperative perception framework, termed QUEST, which let query stream flow among agents. The cross-agent queries are interacted via fusion for co-aware instances and complementation for individual unaware instances. Taking camera-based vehicle-infrastructure perception as a typical practical application scene, the experimental results on the real-world dataset, DAIR-V2X-Seq, demonstrate the effectiveness of QUEST and further reveal the advantage of the query cooperation paradigm on transmission flexibility and robustness to packet dropout. We hope our work can further facilitate the cross-agent representation interaction for better cooperative perception in practice.

Capturing molecular knowledge with representation learning approaches holds significant potential in vast scientific fields such as chemistry and life science. An effective and generalizable molecular representation is expected to capture the consensus and complementary molecular expertise from diverse views and perspectives. However, existing works fall short in learning multi-view molecular representations, due to challenges in explicitly incorporating view information and handling molecular knowledge from heterogeneous sources. To address these issues, we present MV-Mol, a molecular representation learning model that harvests multi-view molecular expertise from chemical structures, unstructured knowledge from biomedical texts, and structured knowledge from knowledge graphs. We utilize text prompts to model view information and design a fusion architecture to extract view-based molecular representations. We develop a two-stage pre-training procedure, exploiting heterogeneous data of varying quality and quantity. Through extensive experiments, we show that MV-Mol provides improved representations that substantially benefit molecular property prediction. Additionally, MV-Mol exhibits state-of-the-art performance in multi-modal comprehension of molecular structures and texts. Code and data are available at https://github.com/PharMolix/OpenBioMed.

Studying protein mutations within amino acid sequences holds tremendous significance in life sciences. Protein language models (PLMs) have demonstrated strong capabilities in broad biological applications. However, due to architectural design and lack of supervision, PLMs model mutations implicitly with evolutionary plausibility, which is not satisfactory to serve as explainable and engineerable tools in real-world studies. To address these issues, we present MutaPLM, a unified framework for interpreting and navigating protein mutations with protein language models. MutaPLM introduces a protein *delta* network that captures explicit protein mutation representations within a unified feature space, and a transfer learning pipeline with a chain-of-thought (CoT) strategy to harvest protein mutation knowledge from biomedical texts. We also construct MutaDescribe, the first large-scale protein mutation dataset with rich textual annotations, which provides cross-modal supervision signals. Through comprehensive experiments, we demonstrate that MutaPLM excels at providing human-understandable explanations for mutational effects and prioritizing novel mutations with desirable properties. Our code, model, and data are open-sourced at https://github.com/PharMolix/MutaPLM.

Motion forecasting is an essential task for autonomous driving, and utilizing information from infrastructure and other vehicles can enhance forecasting capabilities. Existing research mainly focuses on leveraging single-frame cooperative information to enhance the limited perception capability of the ego vehicle, while underutilizing the motion and interaction context of traffic participants observed from cooperative devices. In this paper, we propose a forecasting-oriented representation paradigm to utilize motion and interaction features from cooperative information. Specifically, we present V2X-Graph, a representative framework to achieve interpretable and end-to-end trajectory feature fusion for cooperative motion forecasting. V2X-Graph is evaluated on V2X-Seq in vehicle-to-infrastructure (V2I) scenarios. To further evaluate on vehicle-to-everything (V2X) scenario, we construct the first real-world V2X motion forecasting dataset V2X-Traj, which contains multiple autonomous vehicles and infrastructure in every scenario. Experimental results on both V2X-Seq and V2X-Traj show the advantage of our method. We hope both V2X-Graph and V2X-Traj will benefit the further development of cooperative motion forecasting. Find the project at https://github.com/AIR-THU/V2X-Graph.

Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability.To achieve the best performance for natural language processing (NLP) tasks with just a few samples, it is vital to include as many informative samples as possible and to avoid misleading ones.However, there is no work in prompttuning literature addressing the problem of differentiating informative hard samples from misleading ones in model training, which is challenging due to the lack of supervision signals about the quality of the samples to train a wellperformed model.We propose a framework named Hard Sample Aware Prompt-Tuning (HardPT) to solve the non-differentiable problem in hard sample identification with reinforcement learning, and to strengthen the discrimination of the feature space without changing the original data distribution via an adaptive contrastive learning method.An extensive empirical study on a series of NLP tasks demonstrates the capability of HardPT in few-shot scenarios.HardPT obtains new state-of-the-art results on all evaluated NLP tasks, including pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement), NMLI accuracy to 71.5 (0.7% absolute improvement), TACREV F 1 -score to 28.2 (1.0 absolute improvement), and i2b2/VA F 1 -score to 41.2 (1.3 absolute improvement).…

Utilizing infrastructure and vehicle-side information to track and forecast the behaviors of surrounding traffic participants can significantly improve decision-making and safety in autonomous driving. However, the lack of real-world sequential datasets limits research in this area. To address this issue, we introduce V2X-Seq, the first large-scale sequential V2X dataset, which includes data frames, trajectories, vector maps, and traffic lights captured from natural scenery. V2X-Seq comprises two parts: the sequential perception dataset, which includes more than 15,000 frames captured from 95 scenarios, and the trajectory forecasting dataset, which contains about 80,000 infrastructure-view scenarios, 80,000 vehicle-view scenarios, and 50,000 cooperative-view scenarios captured from 28 intersections' areas, covering 672 hours of data. Based on V2X-Seq, we introduce three new tasks for vehicle-infrastructure cooperative (VIC) autonomous driving: VIC3D Tracking, Online-VIC Forecasting, and Offline-VIC Forecasting. We also provide benchmarks for the introduced tasks. Find data, code, and more up-to-date information at https://github.com/AIR-THU/DAIR-V2X-Seq.

Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, the uncertain temporal asynchrony and limited communication conditions that are present in traffic environments can lead to fusion misalignment and constrain the exploitation of infrastructure data. To address these issues in vehicle-infrastructure cooperative 3D (VIC3D) object detection, we propose the Feature Flow Net (FFNet), a novel cooperative detection framework. FFNet is a flow-based feature fusion framework that uses a feature flow prediction module to predict future features and compensate for asynchrony. Instead of transmitting feature maps extracted from still-images, FFNet transmits feature flow, leveraging the temporal coherence of sequential infrastructure frames. Furthermore, we introduce a self-supervised training approach that enables FFNet to generate feature flow with feature prediction ability from raw infrastructure sequences. Experimental results demonstrate that our proposed method outperforms existing cooperative detection methods while only requiring about 1/100 of the transmission cost of raw data and covers all latency in one model on the DAIR-V2X dataset. The code is available https://github.com/haibao-yu/FFNet-VIC3D.

The user review data have been demonstrated to be effective in solving different recommendation problems. Previous review-based recommendation methods usually employ sophisticated compositional models, such as Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), to learn semantic representations from the review data for recommendation. However, these methods mainly capture the local dependency between neighboring words in a word window, and they treat each review equally. Therefore, they may not be effective in capturing the global dependency between words and tend to be easily biased by noise review information. In this paper, we propose a novel review-based recommendation model, named Review Graph Neural Network (RGNN). Specifically, RGNN builds a specific review graph for each individual user/item, which provides a global view about the user/item properties to help weaken the biases caused by noise review information. A type-aware graph attention mechanism is developed to learn semantic embeddings of words. Moreover, a personalized graph pooling operator is proposed to learn hierarchical representations of the review graph to form the semantic representation for each user/item. We compared RGNN with state-of-the-art review-based recommendation approaches on two real-world datasets. The experimental results indicate that RGNN consistently outperforms baseline methods, in terms of Mean Square Error (MSE).

Artificial intelligence (AI) is a promising technology to transform the healthcare industry. Due to the highly sensitive nature of patient data, federated learning (FL) is often leveraged to build models for smart healthcare applications. Existing deployed FL frameworks cannot address the key issues of varying data quality and heterogeneous data distributions across multiple institutions in this sector. In this paper, we report our experience developing and deploying the Contribution-Aware Federated Learning (CAFL) framework for smart healthcare. It provides an efficient and accurate approach to fairly evaluate FL participants' contribution to model performance without exposing their private data, and improves the FL model training protocol to allow the best performing intermediate models to be distributed to participants for FL training. Since its deployment in Yidu Cloud Technology Inc. in March 2021, CAFL has served 8 well-established medical institutions in China to build healthcare decision support models. It can perform contribution evaluations 2.84 times faster than the best existing approach, and has improved the average accuracy of the resulting models by 2.62% compared to the previous system (which is significant in industrial settings). To our knowledge, it is the first contribution-aware federated learning successfully deployed in the healthcare industry.

Autonomous driving faces great safety challenges for a lack of global perspective and the limitation of long-range perception capabilities. It has been widely agreed that vehicle-infrastructure cooperation is required to achieve Level 5 autonomy. However, there is still NO dataset from real scenarios available for computer vision researchers to work on vehicle-infrastructure cooperation-related problems. To accelerate computer vision research and innovation for Vehicle-Infrastructure Cooperative Autonomous Driving (VICAD), we release DAIR-V2X Dataset, which is the first large-scale, multi-modality, multi-view dataset from real scenarios for VICAD. DAIR-V2X comprises 71254 LiDAR frames and 71254 Camera frames, and all frames are captured from real scenes with 3D annotations. The Vehicle-Infrastructure Cooperative 3D Object Detection problem (VIC3D) is introduced, formulating the problem of collaboratively locating and identifying 3D objects using sensory inputs from both vehicle and infrastructure. In addition to solving traditional 3D object detection problems, the solution of VIC3D needs to consider the temporal asynchrony problem between vehicle and infrastructure sensors and the data transmission cost between them. Furthermore, we propose Time Compensation Late Fusion (TCLF), a late fusion framework for the VIC3D task as a benchmark based on DAIR-V2X. Find data, code, and more up-to-date information at https://thudair.baai.ac.cn/index and https://github.com/AIR-Thu/dair-V2x.

Computational understanding of humor is an important topic under creative language understanding and modeling. It can play a key role in complex human-AI interactions. The challenge here is that human perception of humorous content is highly subjective. The same joke may receive different funniness ratings from different readers. This makes it highly challenging for humor recognition models to achieve personalization in practical scenarios. Existing approaches are generally designed based on the assumption that users have a consensus on whether a given text is humorous or not. Thus, they cannot handle diverse humor preferences well. In this article, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL). Extending a pre-trained language model, FedHumor guides the fine-tuning process by considering diverse distributions of humor preferences from individuals. It incorporates a diversity adaptation strategy into the FL paradigm to train a personalized humor recognition model. To the best of our knowledge, FedHumor is the first text-based personalized humor recognition model through federated learning. Extensive experiments demonstrate the advantage of FedHumor in recognizing humorous texts compared to nine state-of-the-art humor recognition approaches with superior capability for handling the diversity in humor labels produced by users with diverse preferences.

Active learning is able to significantly reduce the annotation cost for data-driven techniques.However, previous active learning approaches for natural language processing mainly depend on the entropy-based uncertainty criterion, and ignore the characteristics of natural language.In this paper, we propose a pre-trained language model based active learning approach for sentence matching.Differing from previous active learning, it can provide linguistic criteria from the pre-trained language model to measure instances and help select more effective instances for annotation.Experiments demonstrate our approach can achieve greater accuracy with fewer labeled training instances.

End-to-end Spoken Language Understanding (SLU) is proposed to infer the semantic meaning directly from audio features without intermediate text representation. In this paper, we explore unsupervised pre-training for End-to-end SLU models by learning representations from large-scale raw audios. The pre-trained model preserves semantic features which benefit the downstream SLU tasks as the learned model weights are further fine-tuned on the task specific training data. Our approach out-perform the state-of-the-art end-to-end SLU system with over 18.33% error reduction.

Most existing works on dialog systems only consider conversation content while neglecting the personality of the user the bot is interacting with, which begets several unsolved issues. In this paper, we present a personalized end-to-end model in an attempt to leverage personalization in goal-oriented dialogs. We first introduce a PROFILE MODEL which encodes user profiles into distributed embeddings and refers to conversation history from other similar users. Then a PREFERENCE MODEL captures user preferences over knowledge base entities to handle the ambiguity in user requests. The two models are combined into the PERSONALIZED MEMN2N. Experiments show that the proposed model achieves qualitative performance improvements over state-of-the-art methods. As for human evaluation, it also outperforms other approaches in terms of task completion rate and user satisfaction.

Conventional chatbots focus on two-party response generation, which simplifies the real dialogue scene.In this paper, we strive toward a novel task of Response Generation on Multi-Party Chatbot (RGMPC), where the generated responses heavily rely on the interlocutors' roles (e.g., speaker and addressee) and their utterances.Unfortunately, complex interactions among the interlocutors' roles make it challenging to precisely capture conversational contexts and interlocutors' information.Facing this challenge, we present a response generation model which incorporates Interlocutor-aware Contexts into Recurrent Encoder-Decoder frameworks (ICRED) for RGMPC.Specifically, we employ interactive representations to capture dialogue contexts for different interlocutors.Moreover, we leverage an addressee memory to enhance contextual interlocutor information for the target addressee.Finally, we construct a corpus for RGMPC based on an existing open-access dataset.Automatic and manual evaluations demonstrate that the ICRED remarkably outperforms strong baselines.

Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao. 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.

Chatbots have drawn significant attention of late in both industry and academia. For most task completion bots in the industry, human intervention is the only means of avoiding mistakes in complex real-world cases. However, to the best of our knowledge, there is no existing research work modeling the collaboration between task completion bots and human workers. In this paper, we introduce CoChat, a dialog management framework to enable effective collaboration between bots and human workers. In CoChat, human workers can introduce new actions at any time to handle previously unseen cases. We propose a memory-enhanced hierarchical RNN (MemHRNN) to handle the one-shot learning challenges caused by instantly introducing new actions in CoChat. Extensive experiments on real-world datasets well demonstrate that CoChat can relieve most of the human workers’ workload, and get better user satisfaction rates comparing to other state-of-the-art frameworks.

Nowadays, it is very common for one person to be in different social networks. Linking identical users across different social networks, also known as the User Identity Linkage (UIL) problem, is fundamental for many applications. There are two major challenges in the UIL problem. First, it's extremely expensive to collect manually linked user pairs as training data. Second, the user attributes in different networks are usually defined and formatted very differently which makes attribute alignment very hard. In this paper we propose CoLink, a general unsupervised framework for the UIL problem. CoLink employs a co-training algorithm, which manipulates two independent models, the attribute-based model and the relationship-based model, and makes them reinforce each other iteratively in an unsupervised way. We also propose the sequence-to-sequence learning as a very effective implementation of the attribute-based model, which can well handle the challenge of the attribute alignment by treating it as a machine translation problem. We apply CoLink to a UIL task of mapping the employees in an enterprise network to their LinkedIn profiles. The experiment results show that CoLink generally outperforms the state-of-the-art unsupervised approaches by an F1 increase over 20%.

Most of the sequence tagging tasks in natural language processing require to recognize segments with certain syntactic role or semantic meaning in a sentence.They are usually tackled with Conditional Random Fields (CRFs), which do indirect word-level modeling over word-level features and thus cannot make full use of segment-level information.Semi-Markov Conditional Random Fields (Semi-CRFs) model segments directly but extracting segment-level features for Semi-CRFs is still a very challenging problem.This paper presents Gated Recursive Semi-CRFs (grSemi-CRFs), which model segments directly and automatically learn segmentlevel features through a gated recursive convolutional neural network.Our experiments on text chunking and named entity recognition (NER) demonstrate that grSemi-CRFs generally outperform other neural models.

Extracting named entities in text and linking extracted names to a given knowledge base are fundamental tasks in applications for text understanding.Existing systems typically run a named entity recognition (NER) model to extract entity names first, then run an entity linking model to link extracted names to a knowledge base.NER and linking models are usually trained separately, and the mutual dependency between the two tasks is ignored.We propose JERL, Joint Entity Recognition and Linking, to jointly model NER and linking tasks and capture the mutual dependency between them.It allows the information from each task to improve the performance of the other.To the best of our knowledge, JERL is the first model to jointly optimize NER and linking tasks together completely.In experiments on the CoNLL'03/AIDA data set, JERL outperforms state-of-art NER and linking systems, and we find improvements of 0.4% absolute F 1 for NER on CoNLL'03, and 0.36% absolute precision@1 for linking on AIDA.

Distributed representations of words (aka word embedding) have proven helpful in solving natural language processing (NLP) tasks. Training distributed representations of words with neural networks has lately been a major focus of researchers in the field. Recent work on word embedding, the Continuous Bag-of-Words (CBOW) model and the Continuous Skip-gram (Skip-gram) model, have produced particularly impressive results, significantly speeding up the training process to enable word representation learning from large-scale data. However, both CBOW and Skip-gram do not pay enough attention to word proximity in terms of model or word ambiguity in terms of linguistics. In this paper, we propose Proximity-Ambiguity Sensitive (PAS) models (i.e. PAS CBOW and PAS Skip-gram) to produce high quality distributed representations of words considering both word proximity and ambiguity. From the model perspective, we introduce proximity weights as parameters to be learned in PAS CBOW and used in PAS Skip-gram. By better modeling word proximity, we reveal the strength of pooling-structured neural networks in word representation learning. The proximity-sensitive pooling layer can also be applied to other neural network applications that employ pooling layers. From the linguistics perspective, we train multiple representation vectors per word. Each representation vector corresponds to a particular group of POS tags of the word. By using PAS models, we achieved a 16.9% increase in accuracy over state-of-the-art models.

With the rapid growing of Web 2.0, people spend more time on social networks such as Facebook and Twitter. In order to know the people they are interacting with, finding the web appearances of them will help the social network users to a great extent. We propose a novel and effective latent factor model to find web appearances of target social network users. Our method solves the name ambiguity problem by simultaneously exploring the link structure of social networks and the web. Experiments on real-world data show the superiority of our method over several baselines.

There are various kinds of valuable semantic information about real-world entities embedded in webpages and databases. Extracting and integrating these entity information from the Web is of great significance. Comparing to traditional information extraction problems, web entity extraction needs to solve several new challenges to fully take advantage of the unique characteristic of the Web. In this paper, we introduce our recent work on statistical extraction of structured entities, named entities, entity facts and relations from Web. We also briefly introduce iKnoweb, an interactive knowledge mining framework for entity information integration. We will use two novel web applications, Microsoft Academic Search (aka Libra) and EntityCube, as working examples.

This article studies the problem of mining entity translation, specifically, mining English and Chinese name pairs. Existing efforts can be categorized into (a) transliteration-based approaches that leverage phonetic similarity and (b) corpus-based approaches that exploit bilingual cooccurrences. These approaches suffer from inaccuracy and scarcity, respectively. In clear contrast, we use under-leveraged resources of monolingual entity cooccurrences crawled from entity search engines, which are represented as two entity-relationship graphs extracted from two language corpora, respectively. Our problem is then abstracted as finding correct mappings across two graphs. To achieve this goal, we propose a holistic approach to exploiting both transliteration similarity and monolingual cooccurrences. This approach, which builds upon monolingual corpora, complements existing corpus-based work requiring scarce resources of parallel or comparable corpus while significantly boosting the accuracy of transliteration-based work. In addition, by parallelizing the mapping process on multicore architectures, we speed up the computation by more than 10 times per unit accuracy. We validated the effectiveness and efficiency of our proposed approach using real-life datasets.

Author disambiguation in digital libraries becomes increasingly difficult as the number of publications and consequently the number of ambiguous author names keep growing. The fully automatic author disambiguation approach could not give satisfactory results due to the lack of signals in many cases. Furthermore, human judgment on the basis of automatic algorithms is also not suitable because the automatically disambiguated results are often mixed and not understandable for humans. In this paper, we propose a Labeling Oriented Author Disambiguation approach, called LOAD, to combine machine learning and human judgment together in author disambiguation. LOAD exploits a framework which consists of high precision clustering, high recall clustering, and top dissimilar clusters selection and ranking. In the framework, supervised learning algorithms are used to train the similarity functions between publications and a clustering algorithm is further applied to generate clusters. To validate the effectiveness and efficiency of the proposed LOAD approach, comprehensive experiments are conducted. Comparing to conventional author disambiguation algorithms, the LOAD yields much more accurate results to assist human labeling. Further experiments show that the LOAD approach can save labeling time dramatically.

This paper introduces the problem of matching people names to their corresponding social network identities such as their Twitter accounts. Existing tools for this purpose build upon naive textual matching and inevitably suffer low precision, due to false positives (e.g., fake impersonator accounts) and false negatives (e.g., accounts using nicknames). To overcome these limitations, we leverage evidences extracted from the Web corpus. In particular, as such an example, weadopt Web document co-occurrences, which can be interpreted as an implicit counterpart of Twitter follower relationships. Using both textual and relational features, we learn a ranking function aggregating these features for the accurate ordering of candidate matches. Another key contribution of this paper is to formulate confidence scoring as a separate problem from relevance ranking. A baseline approach is to use the relevance of the top match itself as the confidence score. In contrast, we train a separate classifier, using not only the top relevance score but also various statistical features extracted from the relevance scores of all candidates, and empirically validate to outperform the baseline approach. We evaluate our proposed system using real-life internetscale entity-relationship and social network graphs.

We demonstrate Product EntityCube, a product recommendation and navigation system. While the unprecedented scale of a product search portal enables to satisfy users with diverse needs, this scale also complicates product recommendation. Specifically, our target application poses a unique challenge of overcoming insufficient user profiles and feedbacks. To address this problem, we organize query results into clusters representing different user perceptions of similarity, and provide a navigational UI to handle personal interests. Specifically, we first discuss hybrid object clustering capturing diverse user interests from millions of Web pages and disambiguating different perceptions using feature-based similarity. We then discuss skyline object ranking to highlight interesting items at each cluster. Our demonstration illustrates how Product EntityCube can enrich user product shopping experiences.

Internet users regularly have the need to find biographies and facts of people of interest. Wikipedia has become the first stop for celebrity biographies and facts. However, Wikipedia can only provide information for celebrities because of its neutral point of view (NPOV) editorial policy. In this paper we propose an integrated bootstrapping framework named BioSnowball to automatically summarize the Web to generate Wikipedia-style pages for any person with a modest web presence. In BioSnowball, biography ranking and fact extraction are performed together in a single integrated training and inference process using Markov Logic Networks (MLNs) as its underlying statistical model. The bootstrapping framework starts with only a small number of seeds and iteratively finds new facts and biographies. As biography paragraphs on the Web are composed of the most important facts, our joint summarization model can improve the accuracy of both fact extraction and biography ranking compared to decoupled methods in the literature. Empirical results on both a small labeled data set and a real Web-scale data set show the effectiveness of BioSnowball. We also empirically show that BioSnowball outperforms the decoupled methods.

The two most important tasks in information extraction from the Web are webpage structure understanding and natural language sentences processing. However, little work has been done toward an integrated statistical model for understanding webpage structures and processing natural language sentences within the HTML elements. Our recent work on webpage understanding introduces a joint model of Hierarchical Conditional Random Fields (HCRFs) and extended Semi-Markov Conditional Random Fields (Semi-CRFs) to leverage the page structure understanding results in free text segmentation and labeling. In this top-down integration model, the decision of the HCRF model could guide the decision making of the Semi-CRF model. However, the drawback of the top-down integration strategy is also apparent, i.e., the decision of the Semi-CRF model could not be used by the HCRF model to guide its decision making. This paper proposed a novel framework called WebNLP, which enables bidirectional integration of page structure understanding and text understanding in an iterative manner. We have applied the proposed framework to local business entity extraction and Chinese person and organization name extraction. Experiments show that the WebNLP framework achieved significantly better performance than existing methods.

Query result clustering has recently attracted a lot of attention to provide users with a succinct overview of relevant results. However, little work has been done on organizing the query results for object-level search. Object-level search result clustering is challenging because we need to support diverse similarity notions over object-specific features (such as the price and weight of a product) of heterogeneous domains. To address this challenge, we propose a hybrid subspace clustering algorithm called Hydra. Algorithm Hydra captures the user perception of diverse similarity notions from millions of Web pages and disambiguates different senses using feature-based subspace locality measures. Our proposed solution, by combining wisdom of crowds and wisdom of data, achieves robustness and efficiency over existing approaches. We extensively evaluate our proposed framework and demonstrate how to enrich user experiences in object-level search using a real-world product search scenarios.

Traditional relation extraction methods require pre-specified relations and relation-specific human-tagged examples. Bootstrapping systems significantly reduce the number of training examples, but they usually apply heuristic-based methods to combine a set of strict hard rules, which limit the ability to generalize and thus generate a low recall. Furthermore, existing bootstrapping methods do not perform open information extraction (Open IE), which can identify various types of relations without requiring pre-specifications. In this paper, we propose a statistical extraction framework called Statistical Snowball (StatSnowball), which is a bootstrapping system and can perform both traditional relation extraction and Open IE.

Every piece of textual data is generated as a method to convey its authors' opinion regarding specific topics. Authors deliberately organize their writings and create links, i.e., references, acknowledgments, for better expression. Thereafter, it is of interest to study texts as well as their relations to understand the underlying topics and communities. Although many efforts exist in the literature in data clustering and topic mining, they are not applicable to community discovery on large document corpus for several reasons. First, few of them consider both textual attributes as well as relations. Second, scalability remains a significant issue for large-scale datasets. Additionally, most algorithms rely on a set of initial parameters that are hard to be captured and tuned. Motivated by the aforementioned observations, a hierarchical community model is proposed in the paper which distinguishes community cores from affiliated members. We present our efforts to develop a scalable community discovery solution for large-scale document corpus. Our proposal tries to quickly identify potential cores as seeds of communities through relation analysis. To eliminate the influence of initial parameters, an innovative attribute-based core merge process is introduced so that the algorithm promises to return consistent communities regardless initial parameters. Experimental results suggest that the proposed method has high scalability to corpus size and feature dimensionality, with more than 15 topical precision improvement compared with popular clustering techniques.

Little work has been done towards an integrated statistical model for understanding webpage structures and processing natural language sentences within the HTML elements. This paper proposed a novel framework called WebNLP which enables bidirectional integration of page structure understanding and text understanding in an iterative manner. Experiments show that the WebNLP framework achieved significantly better performance.

Hierarchical models have been extensively studied in various domains. However, existing models assume fixed model structures or incorporate structural uncertainty generatively. In this paper, we propose Dynamic Hierarchical Markov Random Fields (DHMRFs) to incorporate structural uncertainty in a discriminative manner. DHMRFs consist of two parts -- structure model and class label model. Both are defined as exponential family distributions. Conditioned on observations, DHMRFs relax the independence assumption as made in directed models. As exact inference is intractable, a variational method is developed to learn parameters and to find the MAP model structure and label assignment. We apply the model to a real-world web data extraction task, which automatically extracts product items for sale on the Web. The results show promise.

Recent work has shown the effectiveness of leveraging layout and tag-tree structure for segmenting webpages and labeling HTML elements. However, how to effectively segment and label the text contents inside HTML elements is still an open problem. Since many text contents on a webpage are often text fragments and not strictly grammatical, traditional natural language processing techniques, that typically expect grammatical sentences, are no longer directly applicable. In this paper, we examine how to use layout and tag-tree structure in a principled way to help understand text contents on webpages. We propose to segment and label the page structure and the text content of a webpage in a joint discriminative probabilistic model. In this model, semantic labels of page structure can be leveraged to help text content understanding, and semantic labels ofthe text phrases can be used in page structure understanding tasks such as data record detection. Thus, integration of both page structure and text content understanding leads to an integrated solution of webpage understanding. Experimental results on research homepage extraction show the feasibility and promise of our approach.

The primary function of current Web search engines is essentially relevance ranking at the document level. However, myriad structured information about real-world objects embedded in static Web pages and online Web databases. In this paper, we propose a paradigm shift to enable searching at the object level. In traditional information retrieval models, documents are taken as the retrieval units and the content of a document is considered reliable. However, this reliability assumption is no longer valid in the object retrieval context when multiple copies of information about the same object typically exist. These copies may be inconsistent because of diversity of Web site qualities and the limited performance of current information extraction techniques. In this paper, we propose several language models for Web object retrieval. We test these models on our academic search engine called Libra and compare their performances. 1.

This paper examines the problem of utilizing pseudo-anchor text to help ranking Web objects in vertical search. We adopt a machine learning based approach to extract pseudo-anchor text for a vertical object from its candidate anchor blocks. Experiments in academic search domain indicate that our approach is able to dramatically improve search performance.

Extracting and integrating object information from the Web is of great significance for Web data management. The existing Web information extraction techniques cannot provide satisfactory solution to the Web object extraction task since objects of the same type are distributed in diverse Web sources, whose structures are highly heterogeneous. In this paper, we propose a novel approach called Object-Level Information Extraction (OLIE) to extract Web objects. This approach extends a classic information extraction algorithm, Conditional Random Fields (CRF), by adding Web-specific information. The experimental results show OLIE can significantly improve the Web object extraction accuracy.

Recent work has shown the feasibility and promise of templateindependent Web data extraction. However, existing approaches use decoupled strategies – attempting to do data record detection and attribute labeling in two separate phases. In this paper, we show that separately extracting data records and attributes is highly ineffective and propose a probabilistic model to perform these two tasks simultaneously. In our approach, record detection can benefit from the availability of semantics required in attribute labeling and, at the same time, the accuracy of attribute labeling can be improved when data records are labeled in a collective manner. The proposed model is called Hierarchical Conditional Random Fields. It can efficiently integrate all useful features by learning their importance, and it can also incorporate hierarchical interactions which are very important for Web data extraction. We empirically compare the proposed model with existing decoupled approaches for product information extraction, and the results show significant improvements in both record detection and attribute labeling.

Understanding goals and preferences behind a user's online activities can greatly help information providers, such as search engine and E-Commerce web sites, to personalize contents and thus improve user satisfaction. Understanding a user's intention could also provide other business advantages to information providers. For example, information providers can decide whether to display commercial content based on user's intent to purchase. Previous work on Web search defines three major types of user search goals for search queries: navigational, informational and transactional or resource [1][7]. In this paper, we focus our attention on capturing commercial intention from search queries and Web pages, i.e., when a user submits the query or browse a Web page, whether he/she is about to commit or in the middle of a commercial activity, such as purchase, auction, selling, paid service, etc. We call the commercial intentions behind a user's online activities as OCI (Online Commercial Intention). We also propose the notion of "Commercial Activity Phase" (CAP), which identifies in which phase a user is in his/her commercial activities: Research or Commit. We present the framework of building machine learning models to learn OCI based on any Web page content. Based on that framework, we build models to detect OCI from search queries and Web pages. We train machine learning models from two types of data sources for a given search query: content of algorithmic search result page(s) and contents of top sites returned by a search engine. Our experiments show that the model based on the first data source achieved better performance. We also discover that frequent queries are more likely to have commercial intention. Finally we propose our future work in learning richer commercial intention behind users' online activities.

The Web contains an abundance of useful semistructured information about real world objects, and our empirical study shows that strong sequence characteristics exist for Web information about objects of the same type across different Web sites. Conditional Random Fields (CRFs) are the state of the art approaches taking the sequence characteristics to do better labeling. However, as the information on a Web page is two-dimensionally laid out, previous linear-chain CRFs have their limitations for Web information extraction. To better incorporate the two-dimensional neighborhood interactions, this paper presents a two-dimensional CRF model to automatically extract object information from the Web. We empirically compare the proposed model with existing linear-chain CRF models for product information extraction, and the results show the effectiveness of our model.

In contrast with the current Web search methods that essentially do document-level ranking and retrieval, we are exploring a new paradigm to enable Web search at the object level. We collect Web information for objects relevant for a specific application domain and rank these objects in terms of their relevance and popularity to answer user queries. Traditional PageRank model is no longer valid for object popularity calculation because of the existence of heterogeneous relationships between objects. This paper introduces PopRank, a domain-independent object-level link analysis model to rank the objects within a specific domain. Specifically we assign a popularity propagation factor to each type of object relationship, study how different popularity propagation factors for these heterogeneous relationships could affect the popularity ranking, and propose efficient approaches to automatically decide these factors. Our experiments are done using 1 million CS papers, and the experimental results show that PopRank can achieve significantly better ranking results than naively applying PageRank on the object graph.

Recent work in data integration has shown the importance of statistical information about the coverage and overlap of sources for efficient query processing. Despite this recognition, there are no effective approaches for learning the needed statistics. The key challenge in learning such statistics is keeping the number of needed statistics low enough to have the storage and learning costs manageable. In this paper, we present a set of connected techniques that estimate the coverage and overlap statistics, while keeping the needed statistics tightly under control. Our approach uses a hierarchical classification of the queries and threshold-based variants of familiar data mining techniques to dynamically decide the level of resolution at which to learn the statistics. We describe the details of our method, and, present experimental results demonstrating the efficiency of the learning algorithms and the effectiveness of the learned statistics over both controlled data sources and in the context of BibFinder with autonomous online sources.

Query optimization in data integration requires source coverage and overlap statistics. Gathering and storing the required statistics presents many challenges, not the least of which is controlling the amount of statistics learned. We introduce StatMiner, a novel statistics mining approach which automatically generates attribute value hierarchies, efficiently discovers frequently accessed query classes based on the learned attribute value hierarchies, and learns statistics only with respect to these classes. We describe the details of our method, and present experimental results demonstrating the efficiency and effectiveness of our approach. Our experiments are done in the context of BibFinder, a publicly fielded bibliography mediator.

Recent work in data integration has shown the importance of statistical information about the coverage and overlap of sources for efficient query processing. Despite this recognition there are no effective approaches for learning the needed statistics. The key challenge in learning such statistics is keeping the number of needed statistics low enough to have the storage and learning costs manageable. Naive approaches can become infeasible very quickly. In this paper we present a set of connected techniques that estimate the coverage and overlap statistics while keeping the needed statistics tightly under control. Our approach uses a hierarchical classification of the queries, and threshold based variants of familiar data mining techniques to dynamically decide the level of resolution at which to learn the statistics. We describe the details of our method, and present experimental results demonstrating the efficiency of the learning algorithms and the effectiveness of the learned statistics.

Existing approaches for optimizing queries in data integration use decoupled strategies--attempting to optimize coverage and cost in two separate phases. Since sources tend to have a variety of access limitations, such phased optimization of cost and coverage can unfortunately lead to expensive planning as well as highly inefficient plans. In this paper we present techniques for joint optimization of cost and coverage of the query plans. Our algorithms search in the space of parallel query plans that support multiple sources for each subgoal conjunct. The refinement of the partial plans takes into account the potential parallelism between source calls, and the binding compatibilities between the sources included in the plan. We start by introducing and motivating our query plan representation. We then briefly review how to compute the cost and coverage of a parallel plan. Next, we provide both a System-R style query optimization algorithm as well as a greedy local search algorithm for searching in the space of such query plans. Finally we present a simulation study that demonstrates that the plans generated by our approach will be significantly better, both in terms of planning cost, and in terms of plan execution cost, compared to the existing approaches.