Personalized Learning Path Planning (PLPP) aims to design adaptive learning paths that align with individual goals. While large language models (LLMs) show potential in personalizing learning experiences, existing approaches often lack mechanisms for goal-aligned planning. We introduce Pxplore, a novel framework for PLPP that integrates a reinforcement-based training paradigm and an LLM-driven educational architecture. We design a structured learner state model and an automated reward function that transforms abstract objectives into computable signals. We train the policy combining supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), and deploy it within a real-world learning platform. Extensive experiments validate Pxplore's effectiveness in producing coherent, personalized, and goal-driven learning paths. We release our code and dataset at https://github.com/Pxplore/pxplore-algo.

Event Relation Extraction (ERE) plays a crucial role in understanding document structures by identifying relations between events. However, most existing methods either rely on single-model instances, which often suffer from overconfidence, or adopt multi-agent frameworks that rely on manually designed prompts and heuristics to define agents, making effective optimization difficult. In this article, we propose Debate to Extract (D2E), a novel multi-agent optimization framework for ERE that leverages structured multi-turn debates and specialized agent training to enhance performance. Specifically, to organize the debate, participants are divided into multiple groups, each assigned its own debate topic. This process effectively integrates both cooperation and confrontation. We also incorporate an audience as a crucial participant, whose conclusions, from an observer’s perspective, tend to be more objective. Building on this debate framework, D2E further optimizes the debate participants, combining structured multi-turn debates with agent training. During the debate, agents refine their initial opinions through collaborative interactions. This iterative process generates valuable supervision signals for training, allowing agents to improve their responses progressively. To address the issue of diminishing returns from data diversity, each agent is trained on distinct subsets of generated data, promoting specialization across different task dimensions. Experimental results on the MAVEN-ERE and EventStoryLine datasets show that D2E achieves significant improvements in causal relation extraction, outperforming baseline methods by 12.1% and 4.69%, respectively. Through further analysis of the debate participants’ performance before and after the debate, we find that participation in the debate generally leads to improved ERE performance. This work demonstrates that combining collaborative debate with agent specialization leads to substantial performance gains in event relation extraction tasks.

Future event prediction (FEP) is a long-standing and crucial task in the world, as understanding the evolution of events enables early risk identification, informed decision-making, and strategic planning. Existing work typically treats event prediction as classification tasks and confines the outcomes of future events to a fixed scope, such as yes/no questions, candidate set, and taxonomy, which is difficult to include all possible outcomes of future events. In this article, we introduce OpenEP (an Open -Ended F EP task), which generates flexible and diverse predictions aligned with real-world scenarios. This is mainly reflected in two aspects: firstly, the predictive questions are diverse, covering different stages of event development and perspectives; secondly, the outcomes are flexible, without constraints on scope or format. To facilitate the study of this task, we construct OpenEPBench , a dynamic dataset where events are annotated on the same day they occur. For question construction, we pose questions from seven perspectives, including time, location, event development, event outcome, event impact, event response, and other, to facilitate an in-depth analysis and understanding of the comprehensive evolution of events. For outcome construction, we collect free-form text containing the outcomes as ground truth to provide semantically complete and detail-enriched outcomes. Furthermore, we propose StkFEP , a stakeholder-enhanced FEP framework, that incorporates event characteristics for open-ended settings. Our method extracts stakeholders involved in events to extend questions to gather diverse information. We also collect both contextually relevant events and historically analogous events to reveal potential evolutionary patterns. Experimental results indicate that accurately predicting future events in open-ended settings is challenging for existing LLMs. In addition, we thoroughly summarize the problems encountered in prediction, hoping to provide insights for future research. Code and data are available at: https://github.com/ncepu-eai/OpenEP .

Designing effective English vocabulary question generation tools demands a shift from labor-intensive content creation to large language model (LLM) automation that can adapt to varied educational contexts. Current approaches tend to offer a limited variety of question types, which restricts their practical application in real classroom settings. To better meet the demands of English teaching institutions, we present VocQuiz, a vocabulary question generation system that 1) combines generalization capabilities of LLMs with reliable language resources, including dictionaries, NLP datasets and authentic corpora, to enhance both contextual relevance and linguistic accuracy; 2) supports multiple question types, such as similar word selection and word collocation, to accommodate various instructional requirements; and 3) employs an iterative workflow to iteratively generate and refine questions, ensuring high-quality outputs and consistent assessment standards. VocQuiz offers a practical, deployable solution that helps educators create quiz-based instructional materials, reducing preparation effort while effectively assessing students' mastery of vocabulary.

Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc. Following the conventional instruction-tuning practice, previous works conduct post-training on complex instruction-response pairs generated by feeding complex instructions to advanced LLMs. However, even advanced LLMs cannot follow complex instructions well, thus limiting the quality of generated data. In this work, we find that existing datasets inherently contain implicit complex constraints and propose a novel data generation technique, constraint back-translation. Specifically, we take the high-quality instruction-response pairs in existing datasets and only adopt advanced LLMs to add complex constraints already met by the responses to the instructions, which naturally reduces costs and data noise. In the experiments, we adopt Llama3-70B-Instruct to back-translate constraints and create a high-quality complex instruction-response dataset, named Crab. We present that post-training on Crab improves multiple backbone LLMs' complex instruction-following ability, evaluated on extensive instruction-following benchmarks. We further find that constraint back-translation also serves as a useful auxiliary training objective in post-training. Our code, data, and models are released to facilitate future research.

Educators face substantial workload pressures, with significant time invested in preparing teaching materials. Generating high-quality lecture scripts from multimodal presentations is a particularly demanding aspect of this preparation. This paper introduces EduCraft, a novel system designed to automate Lecture Script Generation (LSG), addressing key difficulties such as comprehensive multimodal understanding, long-context coherence, and instructional design efficacy. EduCraft features a modular architecture comprising: (1) a Multimodal Input Processing pipeline for robust data extraction and association from slides; (2) a core Lecture Script Generation Engine with instruction-guided VLM and Caption+LLM workflows for pedagogical synthesis; (3) an optional Knowledge Augmentation Module using Retrieval-Augmented Generation (RAG) for enhanced factual grounding; and (4) a Model Integration and Deployment Interface supporting diverse AI models and providing a deployable API. Extensive evaluations, including human assessments and a new automated evaluation framework, demonstrate that EduCraft significantly outperforms strong baselines and teacher-refined scripts in producing coherent, readable, and pedagogically sound lecture scripts. By effectively tackling core LSG challenges, EduCraft offers a practical, configurable solution to reduce educator workload and enhance educational content creation. We open-source EduCraft at https://github.com/wyuc/EduCraft.

Long story generation remains a challenge for existing large language models (LLMs), primarily due to two main factors: (1) discourse coherence, which requires plot consistency, logical coherence, and completeness in the long-form generation, and (2) narrative complexity, which requires an interwoven and engaging narrative. In this paper, we present StoryWriter, a modular and open-source multi-agent framework for controllable and scalable long story generation. We conduct both human and automated evaluation, and StoryWriter significantly outperforms existing story generation baselines in both story quality and length. Furthermore, we use StoryWriter to generate a dataset, which contains about 6,000 high-quality long stories, with an average length of 8,000 words. We train the model Llama3.1-8B and GLM4-9B using supervised fine-tuning on LongStory and develop StoryWriterLLAMA and StoryWriterGLM, which demonstrates advanced performance in long story generation. All code, models, and data are made publicly available to encourage further development.

Specialized entity linking (EL) models are well-trained at mapping mentions to unique knowledge base (KB) entities according to a given context. However, specialized EL models struggle to disambiguate long-tail entities due to their limited training data. Meanwhile, extensively pre-trained large language models (LLMs) possess broader knowledge of uncommon entities. Yet, with a lack of specialized EL training, LLMs frequently fail to generate accurate KB entity names, limiting their standalone effectiveness in EL. With the observation that LLMs are more adept at context generation instead of EL execution, we introduce LLM-Augmented Entity Linking (LLMAEL), the first framework to enhance specialized EL models with LLM data augmentation. LLMAEL leverages off-the-shelf, tuning-free LLMs as context augmenters, generating entity descriptions to serve as additional input for specialized EL models. Experiments show that LLMAEL sets new state-of-the-art results across 6 widely adopted EL benchmarks: compared to prior methods that integrate tuning-free LLMs into EL, LLMAEL achieves an absolute 8.9% gain in EL accuracy. We release our code and datasets.

Large language models (LLMs) have been increasingly applied to various domains, which triggers increasing concerns about LLMs' safety on specialized domains, e.g. medicine. Despite prior explorations on general jailbreaking attacks, there are two challenges for applying existing attacks on testing the domain-specific safety of LLMs: (1) Lack of professional knowledge-driven attacks(2) Insufficient coverage of domain knowledge. To bridge this gap, we propose a new task, knowledge-to-jailbreak, which aims to generate jailbreaking attacks from domain knowledge, requiring both attack effectiveness and knowledge relevance. We collect a large-scale dataset with 12,974 knowledge-jailbreak pairs and fine-tune a large language model as jailbreak-generator, to produce domain knowledge-specific jailbreaks. Experiments on 13 domains and 8 target LLMs demonstrate the effectiveness of jailbreak-generator in generating jailbreaks that are both threatening to the target LLMs and relevant to the given knowledge. We also apply our method to an out-of-domain knowledge base, showing that jailbreak-generator can generate jailbreaks that are comparable in harmfulness to those crafted by human experts. Data and code are available at: https://github.com/THU-KEG/Knowledge-to-Jailbreak/.

Despite the outstanding capabilities of large language models (LLMs), knowledge-intensive reasoning still remains a challenging task due to LLMs' limitations in compositional reasoning and the hallucination problem. A prevalent solution is to employ chain-of-thought (CoT) with retrieval-augmented generation (RAG), which first formulates a reasoning plan by decomposing complex questions into simpler sub-questions, and then applies iterative RAG at each sub-question. However, prior works exhibit two crucial problems: inadequate reasoning planning and poor incorporation of heterogeneous knowledge. In this paper, we introduce AtomR, a framework for LLMs to conduct accurate heterogeneous knowledge reasoning at the atomic level. Inspired by how knowledge graph query languages model compositional reasoning through combining predefined operations, we propose three atomic knowledge operators, a unified set of operators for LLMs to retrieve and manipulate knowledge from heterogeneous sources. First, in the reasoning planning stage, AtomR decomposes a complex question into a reasoning tree where each leaf node corresponds to an atomic knowledge operator, achieving question decomposition that is highly fine-grained and orthogonal. Subsequently, in the reasoning execution stage, AtomR executes each atomic knowledge operator, which flexibly selects, retrieves, and operates atomic level knowledge from heterogeneous sources. We also introduce BlendQA, a challenging benchmark specially tailored for heterogeneous knowledge reasoning. Experiments on three single-source and two multi-source datasets show that AtomR outperforms state-of-the-art baselines by a large margin, with absolute F1 score improvements of 9.4% on 2WikiMultihop and 9.5% on BlendQA. We release our code and data https://github.com/THU-KEG/AtomR.git.

The vast pre-existing slides serve as rich and important materials to carry lecture knowledge. However, effectively leveraging lecture slides to serve students is difficult due to the multi-modal nature of slide content and the heterogeneous teaching actions. We study the problem of discovering effective designs that convert a slide into an interactive lecture. We develop Slide2Lecture, a tuning-free and knowledge-regulated intelligent tutoring system that can (1) effectively convert an input lecture slide into a structured teaching agenda consisting of a set of heterogeneous teaching actions; (2) create and manage an interactive lecture that generates responsive interactions catering to student learning demands while regulating the interactions to follow teaching actions. Slide2Lecture contains a complete pipeline for learners to obtain an interactive classroom experience to learn the slide. For teachers and developers, Slide2Lecture enables customization to cater to personalized demands. Slide2Lecture's online deployment has made more than 200K interactions with students in the 3K lecture sessions. We release our implementation at https://github.com/NewEduAI/Release.

Document-level relation extraction (RE) aims to determine the relations between entities scattered across different sentences through reading and reasoning. Existing methods use semantic segmentation to obtain global information among triples by analyzing entity-level matrices. However, complete document input may introduce certain interference, making it challenging to express the underlying relationships. To address this, we propose a novel approach introducing a low-entity redundancy feature map, achieved by removing certain entities. The proposed optimal path filtering (OPF) selects entity-related sentences using heuristic rules and formulates sentence selection as a set cover problem, solved via backtracking pruning. U-Net is then applied to obtain global features. Our experiment achieves state-of-the-art results on two common document-level RE datasets, Re-DocRED and CDR, outperforming previous methods.

Large language models have achieved remarkable success on general NLP tasks, but they may fall short for domain-specific problems. Recently, various Retrieval-Augmented Large Language Models (RALLMs) are proposed to address this shortcoming. However, existing evaluation tools only provide a few baselines and evaluate them on various domains without mining the depth of domain knowledge. In this paper, we address the challenges of evaluating RALLMs by introducing the R-Eval toolkit, a Python toolkit designed to streamline the evaluation of different RAG workflows in conjunction with LLMs. Our toolkit, which supports popular built-in RAG workflows and allows for the incorporation of customized testing data on the specific domain, is designed to be user-friendly, modular, and extensible. We conduct an evaluation of 21 RALLMs across three task levels and two representative domains, revealing significant variations in the effectiveness of RALLMs across different tasks and domains. Our analysis emphasizes the importance of considering both task and domain requirements when choosing a RAG workflow and LLM combination. We are committed to continuously maintaining our platform at https://github.com/THU-KEG/R-Eval to facilitate both the industry and the researchers.

Visual Question Answering based on external Knowledge Bases (KB-VQA) requires a model to incorporate knowledge beyond the content of given image and question for answer prediction. Most existing works made efforts on using graph neural networks or Multi-modal Large Language Models to incorporate external knowledge for answer generation. Despite the promising results, they have limited interpretability and exhibit a deficiency in handling questions with unseen answers. In this paper, we propose a novel interpretable graph routing network (GRN) which explicitly conducts entity routing over a constructed scene knowledge graph step by step for KB-VQA. At each step, GRN keeps an entity score vector representing how likely of each entity to be activated as the answer, and a transition matrix representing the transition probability from one entity to another. To answer the given question, GRN will focus on certain keywords of the question at each step and correspondingly conduct entity routing by transiting the entity scores according to the transition matrix computed referring to the focused question keywords. In this way, it clearly provides the reasoning process of KB-VQA and can handle the questions with unseen answers without distinction. Experiments on the benchmark dataset KRVQA have demonstrated that GRN improves the performance of KB-VQA by a large margin, surpassing existing state-of-the art KB-VQA methods and Multi-modal Large Language Models, as well as shows competent capability in handling unseen answers and good interpretability in KB-VQA.

Pre-trained Language Models (PLMs) which are trained on large text corpus via self-supervised learning method, have yielded promising performance on various tasks in Natural Language Processing (NLP). However, though PLMs with huge parameters can effectively possess rich knowledge learned from massive training text and benefit downstream tasks at the fine-tuning stage, they still have some limitations such as poor reasoning ability due to the lack of external knowledge. Research has been dedicated to incorporating knowledge into PLMs to tackle these issues. In this paper, we present a comprehensive review of Knowledge Enhanced Pre-trained Language Models (KE-PLMs) to provide a clear insight into this thriving field. We introduce appropriate taxonomies respectively for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to highlight these two main tasks of NLP. For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG), and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods. Finally, we point out some promising future directions of KE-PLMs.

Cross-domain recommendations (CDRs), which can leverage the relatively abundant information from a richer domain to improve the recommendation performance in a sparser domain, have attracted great attention due to their flexible recommendation strategies. Nevertheless, existing CDR approaches still suffer from severe data sparsity and low semantic sampling efficiency issues, and hardly employ existing reinforcement learning models to improve cross-domain recommendation accuracy. To this end, we propose a new Knowledge-aware and Deep Reinforced Cross-Domain Recommendation framework over Collaborative Knowledge Graph (KRCDR). Specifically, we formalize the cross-domain recommendation task as a Markov Decision Process, and propose a knowledge-aware dual state representation approach to enhance state representations within and across domains for target users by leveraging knowledge graph information. Then, to improve the training performance, we propose a Constrained Self-supervised Actor-Critic network (CSAC) model, in which a constrained neighbor pruning strategy is devised to narrow the exploration space and improve the sampling efficiency, and the CSAC is developed to improve the recommendation policy. Additionally, in our proposed CSAC model, a self-supervised output layer within domains is used as an actor network to generate the recommendation policy, and a Q-learning output layer across domains is used as a critic network to feedback reward signals. Finally, based on the KRCDR approach, we design a new algorithm to assist in generating cross-domain recommendation results. Extensive experiments have been conducted on several real-world datasets, which demonstrate the superiority of our proposed approach compared with state-of-the-art baseline methods.

In recent years, knowledge graph (KG) has attracted significant attention from academia and industry, resulting in the development of numerous technologies for KG construction, completion, and application. XLORE is one of the largest multilingual KGs built from Baidu Baike and Wikipedia via a series of knowledge modeling and acquisition methods. In this article, we utilize systematic methods to improve XLORE's data quality and present its latest version, XLORE 3, which enables the effective integration and management of heterogeneous knowledge from diverse resources. Compared with previous versions, XLORE 3 has three major advantages: (1) We design a comprehensive and reasonable schema, namely XLORE ontology, which can effectively organize and manage entities from various resources. (2) We merge equivalent entities in different languages to facilitate knowledge sharing. We provide a large-scale entity linking system to establish the associations between unstructured text and structured KG. (3) We design a multi-strategy knowledge completion framework, which leverages pre-trained language models and vast amounts of unstructured text to discover missing and new facts. The resulting KG contains 446 concepts, 2,608 properties, 66 million entities, and more than 2 billion facts. It is available and downloadable online at https://www.xlore.cn/ , providing a valuable resource for researchers and practitioners in various fields.

Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i.e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative. Based on soccer game videos and synchronized commentary data, we present GOAL, a benchmark of over 8.9k soccer video clips, 22k sentences, and 42k knowledge triples for proposing a challenging new task setting as Knowledge-grounded Video Captioning (KGVC). We experimentally test existing state-of-the-art (SOTA) methods on this resource to demonstrate the future directions for improvement in this challenging task. We hope that our data resource (now available at https://github.com/THU-KEG/goal) can serve researchers and developers interested in knowledge-grounded cross-modal applications.

Teaching assistants have played essential roles in the long history of education. However, few MOOC platforms are providing human or virtual teaching assistants to support learning for massive online students due to the complexity of real-world online education scenarios and the lack of training data. In this paper, we present a virtual MOOC teaching assistant, LittleMu with minimum labeled training data, to provide question answering and chit-chat services. Consisting of two interactive modules of heterogeneous retrieval and language model prompting, LittleMu first integrates structural, semi- and unstructured knowledge sources to support accurate answers for a wide range of questions. Then, we design delicate demonstrations named "Chain of Teach" prompts to exploit the large-scale pre-trained model to handle complex uncollected questions. Except for question answering, we develop other educational services such as knowledge-grounded chit-chat. We test the system's performance via both offline evaluation and online deployment. Since May 2020, our LittleMu system has served over 80,000 users with over 300,000 queries from over 500 courses on XuetangX MOOC platform, which continuously contributes to a more convenient and fair education. Our code, services, and dataset will be available at https://github.com/THU-KEG/VTA.

We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet knowledge. GLM-Dialog offers a series of applicable techniques for exploiting various external knowledge including both helpful and noisy knowledge, enabling the creation of robust knowledge-grounded dialogue LLMs with limited proper datasets. To evaluate the GLM-Dialog more fairly, we also propose a novel evaluation method to allow humans to converse with multiple deployed bots simultaneously and compare their performance implicitly instead of explicitly rating using multidimensional metrics. Comprehensive evaluations from automatic to human perspective demonstrate the advantages of GLM-Dialog comparing with existing open source Chinese dialogue models. We release both the model checkpoint and source code, and also deploy it as a WeChat application to interact with users. We offer our evaluation platform online in an effort to prompt the development of open source models and reliable dialogue evaluation systems. All the source code is available on Github.

Student modeling, the task of inferring a student's learning characteristics through their interactions with coursework, is a fundamental issue in intelligent education. Although the recent attempts from knowledge tracing and cognitive diagnosis propose several promising directions for improving the usability and effectiveness of current models, the existing public datasets are still insufficient to meet the need for these potential solutions due to their ignorance of complete exercising contexts, fine-grained concepts, and cognitive labels. In this paper, we present MoocRadar, a fine-grained, multi-aspect knowledge repository consisting of 2,513 exercise questions, 5,600 knowledge concepts, and over 12 million behavioral records. Specifically, we propose a framework to guarantee a high-quality and comprehensive annotation of fine-grained concepts and cognitive labels. The statistical and experimental results indicate that our dataset provides the basis for the future improvements of existing methods. Moreover, to support the convenient usage for researchers, we release a set of tools for data querying, model adaption, and even the extension of our repository, which are now available at https://github.com/THU-KEG/MOOC-Radar.

Knowledge graphs (KGs) can provide users with semantic information and relations among numerous entities and nodes, which can greatly facilitate the performance of recommender systems. However, existing KG-based approaches still suffer from severe data sparsity and may not be effective in capturing the preference features of similar entities across domains. Therefore, in this article, we propose a P reference-aware G raph A ttention network model with C ollaborative K nowledge G raph ( PGACKG ) for cross-domain recommendations. Preference-aware entity embeddings with some collaborative signals are first obtained by exploiting the graph-embedding model, which can transform entities and items in the collaborative knowledge graph into semantic preference spaces. To better learn user preference features, we devise a preference-aware graph attention network framework that aggregates the preference features of similar entities within domains and across domains. In this framework, multi-hop reasoning is employed to assist in the generation of preference features within domains, and the node random walk based on frequency visits is proposed to gather similar preferences across domains for target entities. Then, the final preference features of entities are fused, while a novel C ross-domain B ayesian P ersonalized R anking ( CBPR ) is proposed to improve cross-domain recommendation accuracy. Extensive empirical experiments on four real-world datasets demonstrate that our proposed approach consistently outperforms state-of-the-art baselines. Furthermore, our PGACKG achieves strong performance in different ablation scenarios, and the interaction sparsity experiments also demonstrate that our proposed approach can significantly alleviate the data sparsity issue.

In today's massive news streams, storylines can help us discover related event pairs and understand the evolution of hot events. Hence many efforts have been devoted to automatically constructing news storylines. However, the development of these methods is strongly limited by the size and quality of existing storyline datasets since news storylines are expensive to annotate as they contain a myriad of unlabeled relationships growing quadratically with the number of news events. Working around these difficulties, we propose a sophisticated pre-processing method to filter candidate news pairs by entity co-occurrence and semantic similarity. With the filter reducing annotation overhead, we construct CStory, a large-scale Chinese news storyline dataset, which contains 11,978 news articles, 112,549 manually labeled storyline relation pairs, and 49,832 evidence sentences for annotation judgment. We conduct extensive experiments on CStory using various algorithms and find that constructing news storylines is challenging even for pre-trained language models. Empirical analysis shows that the sample unbalance issue significantly influences model performance, which shall be the focus of future works. Our dataset is now publicly available at https://github.com/THU-KEG/CStory.

Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without the use of pre-aligned entity pairs. The current state-of-the-art (SOTA) self-supervised EA approach draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, it advocates the minimum information requirement for self-supervised EA, while we argue that self-described KG's side information (e.g., entity name, relation name, entity description) shall preferably be explored to the maximum extent for the self-supervised EA task. In this work, we propose an interactive contrastive learning model for self-supervised EA. It conducts bidirectional contrastive learning via building pseudo-aligned entity pairs as pivots to achieve direct cross-KG information interaction. It further exploits the integration of entity textual and structural information and elaborately designs encoders for better utilization in the self-supervised setting. Experimental results show that our approach outperforms the previous best self-supervised method by a large margin (over 9% [email protected] absolute improvement on average) and performs on par with previous SOTA supervised counterparts, demonstrating the effectiveness of the interactive contrastive learning for self-supervised EA. The code and data are available at https://github.com/THU-KEG/ICLEA.

Large-scale pre-trained language models (PLMs) have shown promising advances on various downstream tasks, among which dialogue is one of the most concerned. However, there remain challenges for individual developers to create a knowledge-grounded dialogue system upon such big models because of the expensive cost of collecting the knowledge resources for supporting the system as well as tuning these large models for the task. To tackle these obstacles, we propose XDAI, a knowledge-grounded dialogue system that is equipped with the prompt-aware tuning-free PLM exploitation and supported by the ready-to-use open-domain external knowledge resources plus the easy-to-change domain-specific mechanism. With XDAI, the developers can leverage the PLMs without any fine-tuning cost to quickly create the open-domain dialogue systems as well as easily customize their own domain-specific systems. Extensive experiments including human evaluation, Turing test, and online evaluation have demonstrated the competitive performance of XDAI compared with the state-of-the-art general PLMs and specific PLMs for dialogue. XDAI pilots studies on the exploitation of PLMs and made intriguing findings which could be inspiring for the future research on other PLM-based applications.

The prosperity of massive open online courses provides fodder for plentiful research efforts on adaptive learning. However, current open-access educational datasets are still far from sufficient to meet the need for various topics of adaptive learning. Existing released datasets often cover only small-scale data, lack fine-grained knowledge concepts. They are even difficult to curate and supplement due to platform limitations. In this work, we construct MOOCCubeX, a large, knowledge-centered repository consisting of 4,216 courses, 230,263 videos, 358,265 exercises, 637,572 fine-grained concepts and over 296 million behavioral data of 3,330,294 students, for supporting the research topics on adaptive learning in MOOCs. Licensed by XuetangX, one of the largest MOOC websites in China, we obtain abundant and diverse course resources and student behavioral data and are permitted to make subsequent periodic updates. We propose a framework to accomplish data processing, weakly supervised fine-grained concept graph mining, and data curation to improve usability and richness. Based on the fine-grained concepts, we re-organize the data from the knowledge perspective and acquire more external learning resources from the web. Our repository is now available at https://github.com/THU-KEG/MOOCCubeX.

Detecting and monitoring competitors is fundamental to a company to stay ahead in the global market. Existing studies mainly focus on mining competitive relationships within a single data source, while competing information is usually distributed in multiple networks. How to discover the underlying patterns and utilize the heterogeneous knowledge to avoid biased aspects in this issue is a challenging problem. In this article, we study the problem of mining competitive relationships by learning across heterogeneous networks. We use Twitter and patent records as our data sources and statistically study the patterns behind the competitive relationships. We find that the two networks exhibit different but complementary patterns of competitions. Overall, we find that similar entities tend to be competitors, with a probability of 4 times higher than chance. On the other hand, in social network, we also find a 10 minutes phenomenon: when two entities are mentioned by the same user within 10 minutes, the likelihood of them being competitors is 25 times higher than chance. Based on the discovered patterns, we propose a novel Topical Factor Graph Model. Generally, our model defines a latent topic layer to bridge the Twitter network and patent network. It then employs a semi-supervised learning algorithm to classify the relationships between entities (e.g., companies or products). We test the proposed model on two real data sets and the experimental results validate the effectiveness of our model, with an average of +46% improvement over alternative methods. Besides, we further demonstrate the competitive relationships inferred by our proposed model can be applied in the job-hopping prediction problem by achieving an average of +10.7% improvement.

With the rapid proliferation of social media, increasingly more people express their opinions and reviews (user-generated content (UGC)) on recent news articles through various online services, such as news portals, forums, discussion groups, and microblogs. Clearly, identifying hot topics that users greatly care about can improve readers’ news browsing experience and facilitate research into interaction analysis between news and UGC. Furthermore, it is of great benefit to public opinion monitoring and management for both industry and government agencies. However, it is extremely time consuming, if not impossible, to manually examine the large amount of available social content. In this article, we formally define the news comment alignment problem and propose a novel framework that: (1) automatically extracts topics from a given news article and its associated comments, (2) identifies and extends positive examples with different degrees of confidence using three methods (i.e., hypersphere, density, and cluster chain), and (3) completes the alignment between news sentences and comments through a weighted-SVM classifier. Extensive experiments show that our proposed framework significantly outperforms state-of-the-art methods.

Similarity search is a fundamental problem in network analysis and can be applied in many applications, such as collaborator recommendation in coauthor networks, friend recommendation in social networks, and relation prediction in medical information networks. In this article, we propose a sampling-based method using random paths to estimate the similarities based on both common neighbors and structural contexts efficiently in very large homogeneous or heterogeneous information networks. We give a theoretical guarantee that the sampling size depends on the error-bound ε, the confidence level (1-δ), and the path length T of each random walk. We perform an extensive empirical study on a Tencent microblogging network of 1,000,000,000 edges. We show that our algorithm can return top- k similar vertices for any vertex in a network 300× faster than the state-of-the-art methods. We develop a prototype system of recommending similar authors to demonstrate the effectiveness of our method.

Given an entity in a source domain, finding its matched entities from another (target) domain is an important task in many applications. Traditionally, the problem was usually addressed by first extracting major keywords corresponding to the source entity and then query relevant entities from the target domain using those keywords. However, the method would inevitably fails if the two domains have less or no overlapping in the content. An extreme case is that the source domain is in English and the target domain is in Chinese.

Estimating similarity between vertices is a fundamental issue in network analysis across various domains, such as social networks and biological networks. Methods based on common neighbors and structural contexts have received much attention. However, both categories of methods are difficult to scale up to handle large networks (with billions of nodes). In this paper, we propose a sampling method that provably and accurately estimates the similarity between vertices. The algorithm is based on a novel idea of random path. Specifically, given a network, we perform R random walks, each starting from a randomly picked vertex and walking T steps. Theoretically, the algorithm guarantees that the sampling size R = O(2ε-2 log2 T) depends on the error-bound ε, the confidence level (1 -- δ), and the path length T of each random walk.

Social influence occurs when one’s opinions, emotions, or behaviors are affected by others in a social network. However, social influence takes many forms, and its underlying mechanism is still unclear. For example, how is one’s behavior influenced by a group of friends who know each other and by the friends from different ego friend circles? In this article, we study the social influence problem in a large microblogging network. Particularly, we consider users’ (re)tweet behaviors and focus on investigating how friends in one’s ego network influence retweet behaviors. We propose a novel notion of social influence locality and develop two instantiation functions based on pairwise influence and structural diversity. The defined influence locality functions have strong predictive power. Without any additional features, we can obtain an F1-score of 71.65% for predicting users’ retweet behaviors by training a logistic regression classifier based on the defined influence locality functions. We incorporate social influence locality into a factor graph model, which can further leverage the network-based correlation. Our experiments on the large microblogging network show that the model significantly improves the precision of retweet prediction. Our analysis also reveals several intriguing discoveries. For example, if you have six friends retweeting a microblog, the average likelihood that you will also retweet it strongly depends on the structure among the six friends: The likelihood will significantly drop (only ⅙) when the six friends do not know each other, compared with the case when the six friends know each other.

introduction Free Access Share on Introduction to the Special Issue on Linking Social Granularity and Functions Authors: Qi He LinkedIn LinkedInView Profile , Juanzi Li Tsinghua University Tsinghua UniversityView Profile , Rong Yan Square SquareView Profile , John Yen Pennsylvania State University Pennsylvania State UniversityView Profile , Haizheng Zhang StarMerx LLC StarMerx LLCView Profile Authors Info & Claims ACM Transactions on Intelligent Systems and TechnologyVolume 5Issue 2Article No.: 22pp 1–3https://doi.org/10.1145/2594452Published:30 April 2014Publication History 2citation322DownloadsMetricsTotal Citations2Total Downloads322Last 12 Months4Last 6 weeks2 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Publisher SiteeReaderPDF

Collaborative filtering (CF) is an important and popular technology for recommender systems. However, current CF methods suffer from such problems as data sparsity, recommendation inaccuracy, and big-error in predictions. In this paper, we borrow ideas of object typicality from cognitive psychology and propose a novel typicality-based collaborative filtering recommendation method named TyCo. A distinct feature of typicality-based CF is that it finds "neighbors" of users based on user typicality degrees in user groups (instead of the corated items of users, or common users of items, as in traditional CF). To the best of our knowledge, there has been no prior work on investigating CF recommendation by combining object typicality. TyCo outperforms many CF recommendation methods on recommendation accuracy (in terms of MAE) with an improvement of at least 6.35 percent in Movielens data set, especially with sparse training data (9.89 percent improvement on MAE) and has lower time cost than other CF methods. Further, it can obtain more accurate predictions with less number of big-error predictions.

Detecting and monitoring competitors is fundamental to a company to stay ahead in the global market. Existing studies mainly focus on mining competitive relationships within a single data source, while competing information is usually distributed in multiple networks. How to discover the underlying patterns and utilize the heterogeneous knowledge to avoid biased aspects in this issue is a challenging problem. In this paper, we study the problem of mining competitive relationships by learning across heterogeneous networks. We use Twitter and patent records as our data sources and statistically study the patterns behind the competitive relationships. We find that the two networks exhibit different but complementary patterns of competitions. Our proposed model, Topical Factor Graph Model (TFGM), defines a latent topic layer to bridge the two networks and learns a semi-supervised learning model to classify the relationships between entities (e.g., companies or products). We test the proposed model on two real data sets and the experimental results validate the effectiveness of our model, with an average of +46\% improvement over alternative methods.

Wikipedia becomes one of the largest knowledge bases on the Web. It has attracted 513 million page views per day in January 2012. However, one critical issue for Wikipedia is that articles in different language are very unbalanced. For example, the number of articles on Wikipedia in English has reached 3.8 million, while the number of Chinese articles is still less than half million and there are only 217 thousand cross-lingual links between articles of the two languages. On the other hand, there are more than 3.9 million Chinese Wiki articles on Baidu Baike and Hudong.com, two popular encyclopedias in Chinese. One important question is how to link the knowledge entries distributed in different knowledge bases. This will immensely enrich the information in the online knowledge bases and benefit many applications. In this paper, we study the problem of cross-lingual knowledge linking and present a linkage factor graph model. Features are defined according to some interesting observations. Experiments on the Wikipedia data set show that our approach can achieve a high precision of 85.8% with a recall of 88.1%. The approach found 202,141 new cross-lingual links between English Wikipedia and Baidu Baike.

Abstract This article investigates the dynamic features of social tagging vocabularies in Delicious, Flickr, and YouTube from 2003 to 2008. Three algorithms are designed to study the macro‐ and micro‐tag growth as well as the dynamics of taggers' activities, respectively. Moreover, we propose a Tagger Tag Resource Latent Dirichlet Allocation (TTR‐LDA) model to explore the evolution of topics emerging from those social vocabularies. Our results show that (a) at the macro level, tag growth in all the three tagging systems obeys power law distribution with exponents lower than 1; at the micro level, the tag growth of popular resources in all three tagging systems follows a similar power law distribution; (b) the exponents of tag growth vary in different evolving stages of resources; (c) the growth of number of taggers associated with different popular resources presents a feature of convergence over time; (d) the active level of taggers has a positive correlation with the macro‐tag growth of different tagging systems; and (e) some topics evolve into several subtopics over time while others experience relatively stable stages in which their contents do not change much, and certain groups of taggers continue their interests in them.

We study a novel problem of social context summarization for Web documents. Traditional summarization research has focused on extracting informative sentences from standard documents. With the rapid growth of online social networks, abundant user generated content (e.g., comments) associated with the standard documents is available. Which parts in a document are social users really caring about? How can we generate summaries for standard documents by considering both the informativeness of sentences and interests of social users? This paper explores such an approach by modeling Web documents and social contexts into a unified framework. We propose a dual wing factor graph (DWFG) model, which utilizes the mutual reinforcement between Web documents and their associated social contexts to generate summaries. An efficient algorithm is designed to learn the proposed factor graph model.Experimental results on a Twitter data set validate the effectiveness of the proposed model. By leveraging the social context information, our approach obtains significant improvement (averagely +5.0%-17.3%) over several alternative methods (CRF, SVM, LR, PR, and DocLead) on the performance of summarization.

Current recommendation methods are mainly classified into content-based, collaborative filtering and hybrid methods. These methods are based on similarity measurements among items or users. In this paper, we investigate recommendation systems from a new perspective based on object typicality and propose a novel typicality-based recommendation approach. Experiments show that our method outperforms compared methods on recommendation quality.

Exploring community is fundamental for uncovering the connections between structure and function of complex networks and for practical applications in many disciplines such as biology and sociology. In this paper, we propose a TTR-LDA-Community model which combines the Latent Dirichlet Allocation model (LDA) and the Girvan-Newman community detection algorithm with an inference mechanism. The model is then applied to data from Delicious, a popular social tagging system, over the time period of 2005-2008. Our results show that 1) users in the same community tend to be interested in similar set of topics in all time periods; and 2) topics may divide into several sub-topics and scatter into different communities over time. We evaluate the effectiveness of our model and show that the TTR-LDA-Community model is meaningful for understanding communities and outperforms TTR-LDA and LDA models in tag prediction.

Retweeting is an important action (behavior) on Twitter, indicating the behavior that users re-post microblogs of their friends. While much work has been conducted for mining textual content that users generate or analyzing the social network structure, few publications systematically study the underlying mechanism of the retweeting behaviors. In this paper, we perform an interesting analysis for the problem on Twitter. We have found that almost 25.5% of the tweets posted by users are actually retweeted from friends' blog spaces. Our investigation unveils that for the retweet behaviors, some statistics still follows the power law distribution, while some others violate the state-of-the-art distribution for Web. Based on these important observations, we propose a factor graph model to predict users' retweeting behaviors. Experimental results on the Twitter data set show that our method can achieve a precision of 28.81% and recall of 37.33% for prediction of the retweet behaviors.

In this paper, we consider a novel problem referred to as term filtering with bounded error to reduce the term (feature) space by eliminating terms without (or with bounded) information loss. Different from existing works, the obtained term space provides a complete view of the original term space. More interestingly, several important questions can be answered such as: 1) how different terms interact with each other and 2) how the filtered terms can be represented by the other terms. We perform a theoretical investigation of the term filtering problem and link it to the Geometric Covering By Discs problem, and prove its NP-hardness. We present two novel approaches for both lossless and lossy term filtering with bounds on the introduced error. Experimental results on multiple text mining tasks validate the effectiveness of the proposed approaches.

Modeling ontology of folksonomy provides a way of learning light weight ontology's which is a hot topic investigated recently. Previous approaches for modeling ontology of folksonomy either ignores semantics (synonymy, hyponymy or polysemy) or do not simultaneously consider relationships between actors (users), concepts (tags) and instances(resources) or are based on the idea that title words are responsible for generating tags for resources. Latent semantics and user-tag dependencies instead of user-word dependencies however are extremely important. In this paper we address these problems by introducing a latent topic layer into the traditional tripartite Actor-Concept-Instance graph. We thus propose an Actor-Concept-Instance-Topic (ACIT) approach to model ontology from folksonomy in a unified way by directly using tags and users of resources. We illustrate on Bibsonomy dataset that our proposed approach ACIT outperforms title words based approaches Tag-Topic (TT) and (User-Word-Topic) UWT for modeling the ontology of folksonomy.

Ontology matching, aiming to obtain semantic correspondences between two ontologies, has played a key role in data exchange, data integration and metadata management. Among numerous matching scenarios, especially the applications cross multiple domains, we observe an important problem, denoted as unbalanced ontology matching which requires to find the matches between an ontology describing a local domain knowledge and another ontology covering the information over multiple domains, is not well studied in the community.

In this paper, we study a novel problem of staring people discovery from social networks, which is concerned with finding people who are not only authoritative but also sociable in the social network. We formalize this problem as an optimization programming problem. Taking the co-author network as a case study, we define three objective functions and propose two methods to combine these objective functions. A genetic algorithm based method is further presented to solve this problem. Experimental results show that the proposed solution can effectively find the staring people from social networks.

Ontology alignment identifies semantically matching entities in different ontologies. Various ontology alignment strategies have been proposed; however, few systems have explored how to automatically combine multiple strategies to improve the matching effectiveness. This paper presents a dynamic multistrategy ontology alignment framework, named RiMOM. The key insight in this framework is that similarity characteristics between ontologies may vary widely. We propose a systematic approach to quantitatively estimate the similarity characteristics for each alignment task and propose a strategy selection method to automatically combine the matching strategies based on two estimated factors. In the approach, we consider both textual and structural characteristics of ontologies. With RiMOM, we participated in the 2006 and 2007 campaigns of the Ontology Alignment Evaluation Initiative (OAEI). Our system is among the top three performers in benchmark data sets.

We address the problem of academic conference homepage understanding for the Semantic Web. This problem consists of three labeling tasks - labeling conference function pages, function blocks, and attributes. Different from traditional information extraction tasks, the data in academic conference homepages has complex structural dependencies across multiple Web pages. In addition, there are logical constraints in the data. In this paper, we propose a unified approach, Constrained Hierarchical Conditional Random Fields, to accomplish the three labeling tasks simultaneously. In this approach, complex structural dependencies can be well described. Also, the constrained Viterbi algorithm in the inference process can avoid logical errors. Experimental results on real world conference data have demonstrated that this approach performs better than cascaded labeling methods by 3.6% in F1-measure and that the constrained inference process can improve the accuracy by 14.3%. Based on the proposed approach, we develop a prototype system of use-oriented semantic academic conference calendar. The user simply needs to specify what conferences he/she is interested in. Subsequently, the system finds, extracts, and updates the semantic information from the Web, and then builds a calendar automatically for the user. The semantic conference data can be used in other applications, such as finding sponsors and finding experts. The proposed approach can be used in other information extraction tasks as well.

This paper addresses several key issues in the ArnetMiner system, which aims at extracting and mining academic social networks. Specifically, the system focuses on: 1) Extracting researcher profiles automatically from the Web; 2) Integrating the publication data into the network from existing digital libraries; 3) Modeling the entire academic network; and 4) Providing search services for the academic network. So far, 448,470 researcher profiles have been extracted using a unified tagging approach. We integrate publications from online Web databases and propose a probabilistic framework to deal with the name ambiguity problem. Furthermore, we propose a unified modeling approach to simultaneously model topical aspects of papers, authors, and publication venues. Search services such as expertise search and people association search have been provided based on the modeling results. In this paper, we describe the architecture and main features of the system. We also present the empirical evaluation of the proposed methods.

Name ambiguity is a critical problem in many applications, in particular in the online bibliography systems, such as DBLP and CiteSeer. Previously, several clustering based methods have been proposed although, the problem still presents to be a big challenge for both research and industry communities. In this paper, we present a complementary study to the problem from another point of view. We propose an approach of finding atomic clusters to improve the performance of existing clustering-based methods. We conducted experiments on a dataset from a real-world system: Arnetminer.org. Experiments results show that significant improvements can be obtained by using the proposed atomic clusters finding approach (about +8% and +27% improvements depending on different clustering methods).

In order to manage the increasing amount of RDF data, an RDF repository should provide not only necessary scalability and efficiency, but also sufficient inference capabilities. Though existing RDF repositories have made progress towards this goal, there is still ample space for improving the overall performance. In this paper, we propose a native RDF repository, System II, to pursue a better tradeoff among the system scalability, the query efficiency, and the inference capabilities. System II takes the hypergraph representation for RDF as the data model for its persistent storage, which effectively avoids the costs of data model transformation when accessing RDF data. Based on this native storage scheme, a set of efficient semantic query processing techniques are designed. First, several indices are built to accelerate RDF data access including a value index, a labeling scheme for transitive closure computation, and three triple indices. Second, we propose a hybrid inference strategy under the pD* semantics to support inference for OWL-Lite with a relatively low computational complexity. Finally, we extend the SPARQL algebra to explicitly express inference semantics in logical query plan by defining new algebra operators. The results of performance evaluation on the LUBM benchmark show that System II has a better combined metric value than the other comparable systems.

With the Web content having been changed from homogeneity to heterogeneity, the recommendation becomes a more challenging issue. In this paper, we have investigated the recommendation problem on a general heterogeneous Web social network. We categorize the recommendation needs on it into two main scenarios: recommendation when a person is doing a search and recommendation when the person is browsing the information. We formalize the recommendation as a ranking problem over the heterogeneous network. Moreover, we propose using a random walk model to simultaneously ranking different types of objects and propose a pair-wise learning algorithm to learn the weight of each type of relationship in the model. Experimental results on two real-world data sets show that improvements can be obtained by comparing with the baseline methods.

In a directory ontology, only concepts and hypernym/hyponym relationships between them are defined. Directory ontologies are widely used in many real-world applications such as product catalogues and Web directories. The widely used heterogeneous directories also bring a big challenge for integration of them. Previously, little attentions have been paid attention to the problem in the research community. In this paper, we propose a path similarity based approach for directory ontology matching. We define the concept's local label and the concept's path label. Next, we propose a path similarity method, which combines the local label and path label information. Then, a top-down similarity flooding is utilized to improve the matching result. Our experimental results on the music genre ontologies show that the proposed method can achieve a precision of 78% and a recall of 66%, significantly outperforming the baseline method.

No abstract available.

This paper addresses several key issues in extraction and mining of an academic social network: 1) extraction of a researcher social network from the existing Web; 2) integration of the publications from existing digital libraries; 3) expertise search on a given topic; and 4) association search between researchers. We developed a social network system, called ArnetMiner, based on proposed methods to the above problems. In total, 448,470 researcher profiles and 981,599 publications were extracted/integrated after the system having been in operation for two years. The paper describes the architecture and main features of the system. It also briefly presents the experimental results of the proposed methods.

Name ambiguity problem has been a challenging issue for a long history. In this paper, we intend to make a thorough investigation of the whole problem. Specifically, we formalize the name disambiguation problem in a unified framework. The framework can incorporate both attribute and relationship into a probabilistic model. We explore a dynamic approach for automatically estimating the person number K and employ an adaptive distance measure to estimate the distance between objects. Experimental results show that our proposed framework can significantly outperform the baseline method.

To manage the increasing amount of RDF data, an RDF repository should provide not only necessary scalability and efficiency, but also sufficient inference capabilities. In this paper, we propose a native RDF repository, System, to pursue a better tradeoff among the above requirements. System takes the hypergraph representation for RDF as the data model for its persistent storage, which effectively avoids the costs of data model transformation when accessing RDF data. In addition, a set of efficient semantic query processing techniques are designed. The results of performance evaluation on the LUBM benchmark show that System has a better combined metric value than the other comparable systems.

This paper is concerned with the problem of name disambiguation. By name disambiguation, we mean distinguishing persons with the same name. It is a critical problem in many knowledge management applications. Despite much research work has been conducted, the problem is still not resolved and becomes even more serious, in particular with the popularity of Web 2.0. Previously, name disambiguation was often undertaken in either a supervised or unsupervised fashion. This paper first gives a constraint-based probabilistic model for semi-supervised name disambiguation. Specifically, we focus on investigating the problem in an academic researcher social network (http://arnetminer.org). The framework combines constraints and Euclidean distance learning, and allows the user to refine the disambiguation results. Experimental results on the researcher social network show that the proposed framework significantly outperforms the baseline method using unsupervised hierarchical clustering algorithm.

In this paper, we describe a Semantic Web application that builds a customizable conference calendar. In contrast to previous works aiming at manually creating a list of upcoming/current and past conferences, in this work we aim at providing a semantic conference calendar which automatically extracts information from the web using semantic annotation. In this system, to build a calendar, the user simply needs to specify what conferences he/she is interested in. The system finds, extracts, and updates the semantic information from the Web. We propose a unified approach for semantic annotation of the conference calendar. We also present evaluations of our approach on real-world data.

This paper addresses the issue of researcher profiling. By researcher profiling, we mean building a semantic profile for an academic researcher, by identifying and annotating information from the Web. Previously, person profile annotation was often undertaken separately in an ad-hoc fashion. This paper first gives a formalization of the entire problem and proposes a unified approach to perform the task using Conditional Random Fields (CRF). The paper shows that with introduction of a set of tags, most of the annotation tasks can be performed within this approach. Experiments show that significant improvements over the separated method can be obtained, because the subtasks of annotation are interdependent and should be performed together. The method has been applied to expert finding. Experimental results show that the performance of expert finding can be significantly improved by using the profiling method.

In this paper, we present the design and implementation of our expertise oriented search system, EOS http://www.arnetminer.net. EOS is a researcher social network system. It has gathered information about a half-million computer science researchers from the Web and constructed a social network among the researchers through their co-authorship. In particular, the relationship in the social network information is used in both ranking experts for a given topic and searching for associations between researchers. Our experimental results demonstrate that the proposed methods for expert finding and association search in a social network are both more effective and efficient than the baseline methods.

Addressed in this paper is the issue of semantic relationship extraction from semi-structured documents. Many research efforts have been made so far on the semantic information extraction. However, much of the previous work focuses on detecting `isolated' semantic information by making use of linguistic analysis or linkage information in web pages and limited research has been done on extracting semantic relationship from the semi-structured documents. In this paper, we propose a method for semantic relationship extraction by using the logical information in the semi-structured document (semi-structured document usually has various types of structure information, e.g. a semi-structured document may be hierarchical laid out). To the best of our knowledge, extracting semantic relationships by using logical information has not been investigated previously. A probabilistic approach has been proposed in the paper. Features used in the probabilistic model have been defined.

Current web search mostly relies on the keywords in the web pages. This method lacks of semantics ii many ways. For example, a search for a person by the person's name means to find the web pages that contain the text of the name. On the contrary, search semantic is to find the information about the person in the real world. It is hard to achieve this goal in current content based web search engines because text is not useful during inference. The semantic web brings semantic to current web with formalized knowledge and data that computers can process. Therefore search can be benefit from the inference which is supported by ontology. In this paper, we propose a novel method to enhance the search semantic using ontology language DAML+OIL. Experiment shows preferable results comparing to the traditional search. The conclusion and future work will also be discussed in this paper.

More and more infrastructure software for semantic web has emerged with the popularity of Semantic Web. Now Semantic Web applications are calling for different infrastructure software to support essential ontology operations, such as ontology persistence, ontology consistency, ontology query, ontology management, reasoning and so on. This paper brings forward the vision about integration of ontology operations based on the unified semantic web software platform. It introduces a model in which varied operations of ontology are added, updated and deleted dynamically. Furthermore, a USWP ("Unified Semantic Web Platform") is implemented according to this model. As an ontology platform using the standard of RDF and RQL, the key characteristic of the USWP is that the platform has a "total solution" for the semantic web applications built on an expansible, flexible, scalable and open architecture. Third part's ontology operation modules can be deployed into USWP with a wrapper under the standard of OOU ("Ontology Operation Unit") and can share data flow with other modules using DOOD ("Dynamical Operatin Ontology Domain") dynamically.