基本信息

陈玉博  男    中国科学院自动化研究所 复杂系统认知与决策重点实验室
电子邮件: yubo.chen@nlpr.ia.ac.cn
通信地址: 北京市海淀区中关村东路95号自动化所智能化大厦711办公室

邮政编码:100190

个人主页:https://yubochen.github.io/


课题组招收硕博生、工程师、实习生,欢迎有意向的同学与我联系。

研究领域

自然语言处理:

计算语言学、深度学习下的自然语言处理

知识图谱和信息抽取:

实体识别、实体消歧、关系抽取、事件抽取、事件关系抽取

大模型:

大模型中的知识分析与萃取、知识增强的大模型、面向大模型的数据工程、大模型的能力评测

招生信息


招生专业

081203-计算机应用技术

081104-模式识别与智能系统

招生方向

自然语言处理,知识图谱,信息抽取,事件抽取,大模型,多模态大模型

教育背景

2012-09--2017-07   中国科学院大学   工学博士学位
2008-09--2012-07   北京化工大学   工学学士学位

工作经历

   
工作简历
2019-10~现在, 中国科学院自动化研究所, 副研究员
2017-07~2019-10,中国科学院自动化研究所, 助理研究员
社会兼职
2024-06-15-今,中国中文信息学会青年工作委员会, 副主任
2022-11-29-2024-06-15,中国中文信息学会青年工作委员会, 秘书长
2022-07-01-今,中国科技情报学会信息技术专委会, 委员
2017-07-30-今,中国中文信息学会语言与知识计算委员会, 委员

教授课程

知识图谱
知识图谱与语义计算
知识图谱导论

专利与奖励

奖励信息

  • 2023年获得第 22 届国际语义网大会ISWC 2023(CCF B类会议)最佳张贴论文奖

  • ​2022年入选中国科学院青年创新促进会,2022

  • 2021年获中国电力科学院有限公司科学技术进步奖一等奖

  • 《知识图谱》课程入选中国科学院大学校级研究生优秀课程(2021年)

  • 2020年入选“第五届中国科协青年人才托举工程”, 国家级, 2020

  • 2019年北京市科学技术进步奖一等奖(个人排名第五), 一等奖, 省级, 2019

  • 中国中文信息学会“钱伟长中文信息处理科学技术奖”一等奖(个人排名第四), 一等奖, 专项, 2018

  •  第十九届中国计算语言学大会(CCL 2020)最佳论文奖, 其他, 2020

  •  2020年全国知识图谱与语义计算大会(CCKS 2020)最佳论文奖, 其他, 2020

  •  CCF-腾讯犀牛鸟科研基金-优秀奖, 专项, 2020

  •  CCF-腾讯犀牛鸟科研基金-优秀专利奖, 专项, 2020

  •  中国科学院自动化研究所“十佳员工”, 研究所(学校), 2019

  •  中国科学院自动化研究所模式识别国家重点实验室“优秀员工”, 研究所(学校), 2019

  •  2017年北京市优秀毕业生, 省级, 2017

  •  中国科学院大学优秀毕业生, 研究所(学校), 2017

  •  第五届全国知识图谱与语义计算大会(CCKS 2017)“最佳论文奖”, 其他, 2017

  •  第四届基于自然标注大数据的自然语言处理国际学术研讨会(NLP-NABD 2016)“最佳论文奖”,  其他, 2016


专利成果

  • 基于知识巩固的增量事件识别方法、系统、装置, 发明, 2020, 第 1 作者, 专利号: 202011244409.x

  • 基于联邦学习的分布式语言关系识别方法、系统和装置, 发明, 2020, 第 2 作者, 专利号: 202011285430.4

  • 基于对抗模仿学习的事件识别及分类方法、系统、装置, 发明, 2021, 第 1 作者, 专利号: 201910440322.0

  • 基于自注意力机制的中文命名实体识别方法、系统、装置, 发明, 2020, 第 1 作者, 专利号: 201811621018.8

  • 基于多语注意力机制的事件识别及分类方法及装置, 发明, 2020, 第 1 作者, 专利号: 201711463578.0


出版信息

在TNNLS、ACL、EMNLP、AAAI 等国际重要会议和期刊发表学术论文80 余篇(CCF A/B类),Google Scholar引用量7000余次,其中一篇论文入选ESI高被引论文,两篇论文入选ACL、EMNLP最具影响力论文榜单(Paper Digest评选),获得国际语义网大会ISWC 2023(CCF B类会议)最佳张贴论文奖,并多次获得最佳论文奖(NLP-NABD 2016、CCKS 2017、CCL 2020、CCKS 2020、CCKS-IJCKG 2024),2023、2024年连续入选美国斯坦福大学发布的全球前2%顶尖科学家榜单。出版学术专著两部《知识图谱》、《知识图谱:算法与实践》,入选十三五国家重点图书出版规划教材。连续多年在中国科学院大学主讲《知识图谱》课程,获评2021年中国科学院大学优秀课程。主持国家自然科学基金面上项目、青年基金项目,作为核心骨干参与国家自然科学基金重点项目、2030新一代人工智能重大项目、重点研发计划课题、中国科学院先导专项课题。主持研发的信息抽取和知识图谱构建系统多次获得国际/国内学术评测冠亚军。入选2020年第五届中国科协青年人才托举工程、2022年全球华人AI 青年学者、2022年中国科学院青年创新促进会会员、2022北京智源人工智能青年科学家俱乐部,担任中国中文信息学会青年工作委员会副主任、Data Intelligence编委、中国中文信息学会语言与知识计算专业委员会委员、中国中文信息学会大模型与生成专业委员、中国科学技术情报学会信息技术专业委员会等。获2018年中国中文信息学会“钱伟长中文信息处理科学技术奖”一等奖(个人排名第四),2019年度北京市科学技术进步奖一等奖(个人排名第五)。更全的论文列表请参考:https://yubochen.github.io/publications.html


发表论文
(1) Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 3 作者
(2) A Troublemaker with Contagious jailbreak Makes Chaos in Honest Towns, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 4 作者
(3) Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 3 作者
(4) Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models, The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025), 2025, 第 3 作者
(5) MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models, The Thirteenth International Conference on Learning Representations (ICLR 2025), 2025, 第 4 作者  通讯作者
(6) CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance, The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025), 2025, 第 5 作者
(7) RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 5 作者
(8) Evaluating Personalized Tool-Augmented LLMsfrom the Perspectives of Personalization andProactivity, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 5 作者
(9) Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models, The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025), 2025, 第 4 作者  通讯作者
(10) Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 3 作者
(11) Knowledge Localization: Mission Not Accomplished? Enter Query Localization!, The Thirteenth International Conference on Learning Representations (ICLR 2025), 2025, 第 3 作者
(12) Revealing the Deceptiveness of KnowledgeEditing:A Mechanistic Analysis of SuperficialEditing, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 3 作者
(13) Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents, The 63rd Annual Meeting of the Association for Computational Linguistics(ACL 2025), 2025, 第 4 作者
(14) WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing, FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, 2024, 第 3 作者  通讯作者
(15) DTELS: Towards Dynamic Granularity of Timeline Summarization, arxiv, 2024, 第 5 作者
(16) AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation, arxiv, 2024, 第 5 作者
(17) Oasis: Data Curation and Assessment System for Pretraining of Large Language Models, PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, 2024, 第 2 作者  通讯作者
(18) Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), 2024, 第 4 作者
(19) ZhuJiu-Knowledge: A Fairer Platform for Evaluating Multiple Knowledge Types in Large Language Models, 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024 Demonstration), 2024, 第 5 作者  通讯作者
(20) LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning, arxiv, 2024, 第 5 作者
(21) Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models, PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, 第 5 作者
(22) Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models, FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, 2024, 第 4 作者
(23) Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning, The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024, 第 5 作者
(24) Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models, The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), 2024, 第 5 作者
(25) RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models, arxiv, 2024, 第 7 作者
(26) CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph, PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 3: SYSTEM DEMONSTRATIONS, 2024, 第 2 作者  通讯作者
(27) MULFE: A Multi-Level Benchmark for Free Text Model Editing, PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, 第 4 作者
(28) Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models, arxiv, 2024, 第 4 作者
(29) Continual Few-shot Event Detection via Hierarchical Augmentation Networks, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, 第 3 作者  通讯作者
(30) Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, 第 3 作者  通讯作者
(31) Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons, The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI 2024), 2024, 第 3 作者  通讯作者
(32) Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, 第 4 作者
(33) Joint Entity and Relation Extraction With Set Prediction Networks, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 第 3 作者
(34) LEGO: A Multi-agent Collaborative Framework with Role-playing and Iterative Feedback for Causality Explanation Generation, Proceedings of the 2023 conference on empirical methods in natural language processing (EMNLP 2023, finding), 2023, 第 3 作者
(35) ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models, Proceedings of the 2023 conference on empirical methods in natural language processing (EMNLP 2023, demo), 2023, 第 6 作者  通讯作者
(36) Complex Event Schema Induction with Knowledge-Enriched Diffusion Model, Proceedings of the 2023 conference on empirical methods in natural language processing (EMNLP 2023, finding), 2023, 第 3 作者
(37) EventOA: An Event Ontology Alignment Benchmark Based on FrameNet and Wikidata, Proceedings of the 61th Annual Meeting of the Association for Computational Linguistics(ACL 2023, finding), 2023, 第 3 作者  通讯作者
(38) CogNet2: A Multi-Level Frame Organized Knowledge Base Integrating Linguistic, World and Commonsense Knowledge, Proceedings of the ISWC 2023 Posters, Demos and Industry Tracks: From Novel Ideas to Industrial Practice co-located with 22nd International Semantic Web Conference (ISWC 2023), 2023, 第 4 作者
(39) Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching, Proceedings of the 2023 conference on empirical methods in natural language processing (EMNLP 2023, finding), 2023, 第 4 作者
(40) Event Ontology Completion with Hierarchical Structure Evolution Networks, Proceedings of the 2023 conference on empirical methods in natural language processing (EMNLP 2023), 2023, 第 3 作者
(41) InstructoR: Instructing Unsupervised Conversational Dense Retrieval with Large Language Models, Proceedings of the 2023 conference on empirical methods in natural language processing (EMNLP 2023, finding), 2023, 第 3 作者  通讯作者
(42) Event Process Typing via Hierarchical Optimal Transport, Association for the Advancement of Artificial Intelligence(AAAI 2023), 2023, 第 2 作者
(43) Zero-Shot Cross-Lingual Event Argument Extraction with Language-Oriented Prefix-Tuning, Association for the Advancement of Artificial Intelligence(AAAI 2023), 2023, 第 3 作者
(44) Generating Temporally-ordered Event Sequences via Event Optimal Transport, Proceedings of the 29th International Conference on Computational Linguistics(COLING 2022), 2022, 第 2 作者
(45) Multi-turn and Multi-Granularity Reader for Document-level Event Extraction, ACM Transactions on Asian and Low-Resource Language Information Processing(ACM TALLIP), 2022, 第 2 作者
(46) Document-Level Relation Extraction via Pair-Aware and Entity-Enhanced Representation Learning, Proceedings of the 29th International Conference on Computational Linguistics(COLING 2022), 2022, 第 3 作者
(47) A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing, The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), 2022, 第 3 作者
(48) CN-AutoMIC: Distilling Chinese Commonsense Knowledge from Pretrained Language Models, The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), 2022, 第 3 作者
(49) CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics(ACL 2022)demo, 2022, 第 7 作者
(50) Augmentation, Retrieval, Generation: Event Sequence Prediction with a Three-Stage Sequence-to-Sequence Approach, Proceedings of the 29th International Conference on Computational Linguistics(COLING 2022), 2022, 第 3 作者
(51) Script Event Prediction via Multilingual Event Graph Networks, ACM Transactions on Asian and Low-Resource Language Information Processing (ACM TALLIP), 2022, 第 2 作者
(52) What the role is vs. What plays the role:Semi-supervised Event Argument Extraction via Dual Question Answering, AAAI 2021, 2021, 第 2 作者
(53) CogNet: Bridging Linguistic Knowledge, World Knowledge and Commonsense Knowledge, AAAI 2021 Demo, 2021, 第 2 作者
(54) Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks, ACL 2021, 2021, 第 3 作者
(55) Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification, EMNLP 2021, 2021, 第 2 作者
(56) Distantly Supervised Relation Extraction in Federated Settings, EMNLP 2021, 2021, 第 2 作者
(57) CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet, ACL 2021 Demo, 2021, 第 2 作者
(58) Automatic ICD Coding via Interactive Shared Representation Networks with Self-distillation Mechanism, ACL 2021, 2021, 第 3 作者
(59) A Large-Scale Chinese Multimodal NER Dataset with Speech Clues, 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (ACL-IJCNLP 2021), VOL 1, 2021, 第 3 作者
(60) Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement, ACL FINDINGS 2021, 2021, 第 3 作者
(61) A Large-Scale Chinese NER Dataset with Speech Clues., ACL 2021, 2021, 第 3 作者
(62) Extracting Events and Their Relations from Texts: A Survey on Recent, AI Open, 2021, 第 2 作者
(63) Set Generation Networks for End-to-End Knowledge Base Population, EMNLP 2021, 2021, 第 3 作者
(64) Multi-Task Self-Supervised Learning for Script Event Prediction, CIKM 2021, 2021, 第 2 作者
(65) Uncertainty-Aware Self-Training for Semi-Supervised Event Temporal Relation Extraction, CIKM 2021, 2021, 第 3 作者
(66) Multi-Sentence Argument Linking via An Event-Aware Hierarchical Encoder, CIKM 2021, 2021, 第 2 作者
(67) Named Entity Recognition via Noise Aware Training Mechanism with Data Filter, ACL 2021 findings, 2021, 第 2 作者
(68) Document-level Event Extraction via Parallel Prediction Networks, ACL 2021, 2021, 第 3 作者
(69) LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification, ACL 2021, 2021, 第 3 作者
(70) Incorporate Lexicon into Self-training: A Distantly Supervised Chinese Medical NER, NLPCC, 2021, 第 5 作者
(71) CroAno : A Crowd Annotation Platform for Improving Label Consistency of Chinese NER Dataset, EMNLP 2021 Demo, 2021, 第 4 作者
(72) Probing into the Root: A Dataset for Reason Extraction of Structural Events from Financial Documents, EACL 2021, 2021, 第 3 作者
(73) NSRL: Named Entity Recognition with Noisy Labels via Selective Review Learning, CCKS, 2021, 第 2 作者
(74) Event Extraction as Machine Reading Comprehension, EMNLP 2020, 2020, 第 2 作者
(75) Knowledge Guided Metric Learning for Few-Shot Text Classification, naacl 2020, 2020, 第 2 作者
(76) Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes, 58th Annual Meeting of the Association-for-Computational-Linguistics (ACL), 2020, 第 4 作者
(77) Incremental Event Detection via Knowledge Consolidation Networks, EMNLP, 2020, 第 2 作者
(78) Multi-Specialty Domain Adaptation for Chinese Medical Named Entity Recognition, CCKS 2020, 2020, 第 3 作者
(79) FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction, EMNLP, 2020, 第 2 作者
(80) How Does Context Matter? On the Robustness of Event Detection with Context-Selective Mask Generalization, (EMNLP 2020)Findings, 2020, 第 2 作者
(81) Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information, SCIENCE CHINAInformationSciences(SClS), 2020, 第 2 作者  通讯作者
(82) HyperCore: Hyperbolic and Co-graph Representation for Automatic ICD Coding, ACL, 2020, 第 2 作者
(83) Towards Causal Explanation Detection with Pyramid Salient-Aware Network, CCL 2020, 2020, 第 2 作者
(84) Knowledge Enhanced Event Causality Identification with Mention Masking Generalizations, IJCAI, 2020, 第 2 作者
(85) Chinese Named Entity Recognition via Adaptive Multi-pass Memory Network with Hierarchical Tagging Mechanism, China National Conference on Chinese Computational Linguistics (CCL 2020), 2020, 第 2 作者
(86) Meta learning for Event Argument Extraction via Domain-Specific Information Enhanced, CCKS, 2020, 第 2 作者
(87) Extracting event and their relations from texts: A survey on recent research progress and challenges, AI OPEN, 2020, 第 2 作者
(88) Exploiting the Ground-Truth: An Adversarial Imitation Based Knowledge Distillation Approach for Event Detection, 33rd AAAI Conference on Artificial Intelligence / 31st Innovative Applications of Artificial Intelligence Conference / 9th AAAI Symposium on Educational Advances in Artificial Intelligence, 2019, 第 2 作者
(89) Event Co-reference Resolution via a Multi-loss Neural Network without Using Argument Information, SCIENCE CHINA Information Sciences, 2019, 第 2 作者  通讯作者
(90) Relation and Fact Type Supervised Knowledge Graph Embedding via Weighted Scores, 18th China National Conference on Computational Linguistics (CCL), 2019, 第 2 作者
(91) Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network, EMNLP 2019, 2019, 
(92) Neural Cross-Lingual Event Detection with Minimal Parallel Resources, EMNLP 2019, 2019, 
(93) Event co-reference resolution via a multi-loss neural network without using argument information, SCIENCE CHINA. INFORMATION SCIENCE, 2019, 第 2 作者
(94) 基于联合标注和全局推理的篇章级事件抽取, Document-level Event Extraction Based on Joint Labeling and Global Reasoning, 中文信息学报, 2019, 第 3 作者
(95) Event co-reference resolution via a multi-loss neural net work without using argument information, Event co-reference resolution via a multi-loss neural network without using argument information, 中国科学:信息科学(英文版), 2019, 第 2 作者  通讯作者
(96) Adversarial Training for Relation Classification with Attention based Gate Mechanism, CCKS 2018, 2018, 第 1 作者
(97) DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data, 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2018): PROCEEDINGS OF SYSTEM DEMONSTRATIONS, 2018, 第 2 作者
(98) Event Detection via Gated Multilingual Attention Mechanism, 2018, 第 2 作者
(99) Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms., EMNLP2018(CCF B), 2018, 
(100) Event Detection via Gated Multilingual Attention Mechanism, 32nd AAAI Conference on Artificial Intelligence / 30th Innovative Applications of Artificial Intelligence Conference / 8th AAAI Symposium on Educational Advances in Artificial Intelligence, 2018, 第 2 作者
(101) Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism., EMNLP2018(CCF B), 2018, 
(102) Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms, PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, 第 2 作者
(103) Improving Event Detection via Information Sharing Among Related Event Types, CHINESE COMPUTATIONAL LINGUISTICS AND NATURAL LANGUAGE PROCESSING BASED ON NATURALLY ANNOTATED BIG DATA, CCL 2017, 2017, 第 2 作者
(104) Automatically Labeled Data Generation for Large Scale Event Extraction, PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 1, 2017, 第 1 作者  通讯作者
(105) Attention-based Event Relevance Model for Stock Price Movement Prediction, 2017, 第 1 作者
(106) Automatically Labeled Data Generation for Large Scale Event Extraction, 2017, 第 1 作者
(107) Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms, 2017, 第 3 作者
(108) Improving Event Detection via Information Sharing among Related Event Types, 2017, 第 4 作者
(109) Event Extraction via Bidirectional Long Short-Term Memory Tensor Neural Networks, 2016, 第 1 作者
(110) Leveraging FrameNet to Improve Automatic Event Detection, 2016, 第 5 作者
(111) 融合多种特征的实体链接技术研究, Entity Linking Based on Multiple Features, 中文信息学报, 2016, 第 2 作者
(112) Leveraging FrameNet to Improve Automatic Event Detection, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2016, 第 2 作者
(113) Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks, 2015, 第 1 作者
(114) Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks, PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, 2015, 第 1 作者  通讯作者
(115) Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks, 2015, 
(116) Learning the Distinctive Pattern Space Features for Relation Extraction, 2014, 第 2 作者
(117) The CASIA Entity linking System at TAC 2013, 2014, 第 3 作者
(118) Group Non-negative Matrix Factorization with Natural Categories for Question Retrieval in Community Question Answer Archives, COLING 2014, 2014, 第 1 作者
(119) 基于表示学习的中文分词算法探索, Chinese Word Segment Based on Character Representation Learning, 中文信息学报, 2013, 第 3 作者
(120) Walk and learn: A two-stage approach for opinion words and opinion targets co-extraction, WWW 2013 Companion - the 22nd International Conference on World Wide Web, 2013, 
(121) Towards Faster and Better Retrieval Models for Question Search, CIKM-2013, 2013, 
(122) CASIA@QALD-3: A Question Answering System over Linked Data, PRO-CEEDINGS OF THE CROSS-LANGUAGE EVALUATION FORUM, 2013, 
(123) Mining opinion words and opinion targets in a two-stage framework, ACL 2013 - 51st Annual Meeting of the Association for Computational Linguistics, the Conference, 2013, 
发表著作

《知识图谱》, Knowledge Graph, 高等教育出版社, 2018-12, 第 4 作者

《知识图谱:算法与实践》, Knowledge Graph:Algorithm and Practice, 高等教育出版社, 2022-3, 第 4 作者


科研活动

   
科研项目
( 1 ) 面向非结构化文本的大规模事件信息抽取关键技术研究, 负责人, 国家任务, 2019-01--2021-12
( 2 ) 知识获取与知识图谱, 负责人, 国家任务, 2019-01--2021-12
( 3 ) 大规模多粒度军事知识体系构建与集成平台, 参与, 中国科学院计划, 2020-11--2025-11
( 4 ) 面向军事博弈的知识体系 构建与服务平台, 负责人, 研究所自选, 2021-04--2023-04
( 5 ) 以自然语言为核心的语义理解研究, 参与, 国家任务, 2020-11--2023-10
( 6 ) 面向抑郁症智能诊疗的可解释对话系统研究, 参与, 中国科学院计划, 2020-01--2022-12
( 7 ) 面向案件审判全流程的智能问答技术及平台, 参与, 国家任务, 2018-07--2021-06
( 8 ) 知识关联与事件推理类问题求解关键技术与系统, 参与, 国家任务, 2019-05--2022-04
( 9 ) 大规模知识关联和文本语义计算方法及应用验证, 参与, 国家任务, 2016-01--2020-12
( 10 ) 建设《中国大百科全书》第三版百科知识图谱, 参与, 企业委托, 2017-12--2018-12
( 11 ) 知识图谱自动构建技术合作项目, 参与, 企业委托, 2017-07--2019-08
( 12 ) 症状知识图谱的构建及应用, 参与, 企业委托, 2018-09--2020-11
( 13 ) 金融知识图谱和问答系统, 参与, 企业委托, 2016-12--2019-12
( 14 ) 面向对话文本的事件知识抽取关键技术研究, 负责人, 企业委托, 2019-01--2021-12
( 15 ) 事件图谱构建与应用关键技术研究, 负责人, 企业委托, 2020-03--2021-03
( 16 ) 面向复杂应用场景的事件知识抽取关键技术研究, 负责人, 国家任务, 2022-01--2025-12
( 17 ) 中科院青促会项目, 负责人, 中国科学院计划, 2022-01--2025-12
参与会议
(1)Knowledge Analysis, Extraction and Enhancement in Pre-trained Language Models   2023-10-12
(2)预训练语言模型中的知识分析、萃取和增强   第二十二届全国计算语言学大会(CCL 2023)   2023-08-03
(3)信息抽取前沿技术综述   第十八届中国计算语言学大会(CCL 2019)   2019-10-18
(4)Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms   2018-11-04
(5) Automatically Labeled Data Generation for Large Scale Event Extraction   2017-07-30
(6)Event Extraction via Bidirectional Long Short-Term Memory Tensor Neural Networks   2016-10-14
(7)Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks   2015-07-26

合作情况

   
项目协作单位

华为

云知声

蚂蚁金服

阿里巴巴

Baidu

Tecent

中国大百科出版集团

指导/协助指导学生

已毕业学生:

刘健  博士研究生 (毕业去向:北京交通大学)

左新宇 博士研究生 (毕业去向:腾讯)

何霖 硕士研究生(毕业去向:京东)

隋典伯 博士研究生(毕业去向:哈尔滨工业大学(威海))

李筑聪 硕士研究生(毕业去向:复旦攻读博士学位)

杨航 博士研究生(毕业去向:百度)

曹鹏飞 博士研究生(毕业去向:中科院自动化所)

周波 博士研究生(毕业去向:华为)

黄修胜  硕士研究生(毕业去向:北京智源人工智能研究院攻读博士学位)

王晨皓  博士研究生(毕业去向:腾讯
付佳   硕士研究生(毕业去向:快手

谢海宁   硕士研究生(毕业去向:腾讯

苑红榜  硕士研究生 毕业去向:复旦攻读博士学位

秦晓彤 硕士研究生毕业去向:军官计划

陈宇恒 硕士研究生毕业去向:华为

杜鹏帆 硕士研究生毕业去向:智谱




在读学生:

周阳     博士研究生

李嘉淳  博士研究生

门天逸 博士研究生

张晨龙 硕士研究生

谢甲宽 直博生

郝煜朴 博士研究生

常傲   硕士研究生

金承远  硕士研究生

黄东琦 硕士研究生

杜一杰 硕士研究生


实习生:

沈佳俊  (中国科学院大学)

何开煜 (北京科技大学)

穆文哲(中国矿业大学)

周桐   (北京邮电大学,实习已结束,留组工作)

张保礼 (北京邮电大学,实习已结束,留组工作)

罗坤  (北京科技大学,实习已结束,北京智源人工智能研究院攻读博士学位

闫晨薇  (北京邮电大学,实习已结束,推免北邮博士)
蔡硕玮 (华南理工大学,实习已结束,香港科大攻读硕士)

吴顺 (北京交通大学,实习已结束,留组工作)

薛智朋 (北京交通大学,实习已结束,留组工作)

杨语晴 (中国科学院大学,实习已结束,保送复旦大学)

周宇洋  (北京邮电大学,实习已结束,香港攻读博士学位

干震   (北京化工大学,实习已结束,滴滴