赵东岩 English

北京大学王选计算机研究所研究员，博士生导师，享受国务院特殊津贴专家。

      办公电话：(86)10-82529252

      电子邮件：zhaodongyan@pku.edu.cn

      研究室主页：网络信息处理研究室

 

    北京大学王选计算机研究所研究员，博士生导师，国务院特殊津贴获得者。1987年进入北京大学计算机系本科学习，1991、1994年分别获得北京大学理学学士和硕士学位。1997年起，北京大学计算机应用技术专业在职博士生，2000年获得理学博士学位。

   主要研究方向为自然语言处理、大规模语义数据管理、基于知识的智能服务技术。中国计算机学会（CCF）杰出会员，CCF自然语言处理专委会执行委员（2010-2019年担任秘书长）、CCF大数据专家委员会执行委员（2013年起）、CCF网络与数据通信专委会执行委员（2010年起），中文信息学会社会媒体处理专委会常委，信息技术新工科产学研联盟理事；全国中文新闻信息标准化技术委员会副秘书长，全国新闻出版信息标准化技术委员会委员。2025年起，担任电子出版新技术国家工程中心主任，中国新闻技术工作者联合会理事，中国印刷技术协会常务理事。

  近年来承担国家自然科学基金、重点研发计划等国家级项目18项、主持9项，省部级科研项目8项、主持4项，担任新一代人工智能国家科技重大专项首席专家（“面向自然语言的语义分析研究”，2020AAA0106600，基础研究类）；发表学术论文200余篇（包括ACL、NuerIPS、AAAI、IJCAI，AI Journal、TOIS、TKDE等CCF A类会议和期刊论文100余篇）；授权发明专利23项；先后七次获得国家和省部级奖励，包括 2006年度国家科技进步二等奖（排名第一）。个人获第十届中国青年科技奖（2007年）和北京市第七届“科技之光”技术创新特别奖等荣誉。

  长期从事自然语言处理和大规模语义数据管理的前沿研究工作。近五年来牵头研制了高效高质量知识图谱构建技术和问道知识云系统、基于领域知识图谱的自然语言对话技术与法律领域智能对话系统、可控对话生成技术与法律文本生成系统、预训练语言模型压缩技术与多模态语义模型，开发了金融知识图谱构建系统与基于AI智能选股的量化基金投资平台等一系列自然语言理解与认知智能的前沿技术与行业应用。

  本人主持研发了报业数字资产管理系统，项目整体技术水平和应用规模达到并部分超过国际先进水平，并广泛应用于全球500余家中文报社，市场占有率达85%。该项目获2006年度国家科技进步二等奖。

  作为秘书长参与创办了CCF中文信息技术专委会学术年会NLPCC（CCF 国际自然语言处理与中文计算会议），并已组织7年专委会的各项活动；专委会连续六年被评为CCF优秀专委会。NLPCC是国内学术机构创办的自然语言处理领域的第一个国际学术会议，连续6年录用率低于23%，为国内NLP领域的快速发展做出了贡献。2019年，NLPCC会议成为CCF推荐的C类会议。

 2021年以来发表的主要文章

    Journal & Transaction Papers:


  • Shuo Shang, Xin Cheng, Yiren Xiong, Feng Guo, Shen Gao, Xiuying Chen, Feng Wang, Yongbo Wang, Dongyan Zhao, Rui Yan: Personalized Review Summarization by Using Graph-Based Retrieval Augmemted Generation. IEEE TKDE  37(11): 6582-6596 (2025) (CCF Rank A)

  • Xiao Liu, Da Yin, Chen Zhang, Dongyan Zhao, Yansong Feng: Eliciting and Improving Causal Reasoning with Conditional Statements.  Computational Linguistics 51(2) June 2025

  • Shen Gao, Haotong Zhang, Xiuying Chen, Chongyang Tao, Dongyan Zhao, Rui Yan: A Trend of AI Conference Convergence in Similarity: An Empirical Study Through Trans-Temporal Heterogeneous Graph. IEEE TKDE 35(9): 9642-9655 (2023) (CCF Rank A)

  • Jiazhan Feng, Chongyang Tao, Xueliang Zhao, Dongyan Zhao: Learning Multi-turn Response Selection in Grounded Dialogues with Reinforced Knowledge and Context Distillation. ACM TOIS. 41(4): 115:1-115:27 (2023) (CCF Rank A)

  • Xiuying Chen, Mingzhe Li, Shen Gao, Zhangming Chan, Dongyan Zhao, Xin Gao, Xiangliang Zhang, Rui Yan: Follow the Timeline! Generating an Abstractive and Extractive Timeline Summary in Chronological Order. ACM TOIS 41(1): 9:1-9:30 (2023) (CCF Rank A)

  • Youhuan Li, Lei Zou, M. Tamer Özsu, Dongyan Zhao: Space-Efficient Subgraph Search Over Streaming Graph With Timing Order Constraint. IEEE TKDE. 34(9): 4453-4467 (2022) (CCF Rank A)


  • Zhibin Chen, Yuting Wu, Yansong Feng, Dongyan Zhao: Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs. Data Intelligence 4(1): 20-40 (2022)

  • Chen Zhang, Yuxuan Lai, Yansong Feng, Dongyan Zhao: A Review of Deep Learning in Question Answering Over Knowledge Bases. AI Open 2: 205-215 (2021)

  • Luozheng Li, Peipei Song, Dan Zhang, Dongyan Zhao: A New Word Mining Method Based on Fast-text Model. Int. J. Asian Lang. Process. 31(2): 2250001:1-2250001:11 (2021)

  • Peng Peng, Qi Ge, Lei Zou, M. Tamer Özsu, Zhiwei Xu, Dongyan Zhao: Optimizing Multi-Query Evaluation in Federated RDF Systems. IEEE TKDE 33(4): 1692-1707 (2021) (CCF Rank A)

  • Shen Gao, Xiuying Chen, Li Liu, Dongyan Zhao, Rui Yan: Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog. ACM TOIS 39(2): 12:1-12:32 (2021) (CCF Rank A)

  • Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, Rui Yan: Meaningful Answer Generation of E-Commerce Question-Answering. ACM TOIS 39(2): 18:1-18:26 (2021) (CCF Rank A)

  • Ruijian Xu, Chongyang Tao, Jiazhan Feng, Wei Wu, Rui Yan, Dongyan Zhao: Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues. ACM TOIS 39(4): 44:1-44:28 (2021)  (CCF Rank A)

  • Juntao Li, Chang Liu, Chongyang Tao, Zhangming Chan, Dongyan Zhao, Min Zhang, Rui Yan: Dialogue History Matters! Personalized Response Selection in Multi-Turn Retrieval-Based Chatbots. ACM TOIS 39(4): 45:1-45:25 (2021)  (CCF Rank A)

  • Rui Yan, Weiheng Liao, Dongyan Zhao, Ji-Rong Wen: Multi-Response Awareness for Retrieval-Based Conversations: Respond with Diversity via Dynamic Representation Learning. ACM TOIS 39(4): 54:1-54:29 (2021)  (CCF Rank A)


    Conference Papers:


  • Zekai Zhang, Yiduo Guo, Jiuheng Lin, Shanghaoran Quan, Huishuai Zhang, Dongyan Zhao: English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge. EMNLP 2025:1185–1196

  • Tan Yue, Rui Mao, Zilong Song, Zonghai Hu, Dongyan Zhao:       F2TEval: Human-Aligned Multi-Dimensional Evaluation for Figure-to-Text Task.  EMNLP 2025: 3932–3948

  • Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Jiansheng Wei, Huishuai Zhang, Dongyan Zhao: VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format.   EMNLP 2025: 6338–6359

  • Danlong Yuan, Jiahao Liu, Bei Li, Huishuai Zhang, Jingang Wang, Xunliang Cai, Dongyan Zhao: ReMamba: Equip Mamba with Effective Long-Sequence Modeling. EMNLP 2025:6830–6840

  • Tan Yue, Xuzhao Shi, Rui Mao, Zilong Song, Zonghai Hu, Dongyan Zhao: AnaFig: A Human- Aligned Dataset for Scientific Figure Analysis. ACM MM 2025: 12837 – 12843 (CCF Rank A)

  • Jianxin Liang, Xiaojun Meng, Yueqian Wang, Chang Liu, Qun Liu, Dongyan Zhao. End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling. NLPCC 2025 (CCF Distinguished Paper)

  • Xiaoxi Sun, Jianxin Liang, Yueqian Wang, Huishuai Zhang, Dongyan Zhao: Understanding Visual Detail Hallucinations of Large Vision-Language Models. IJCAI 2025: 1900-1908 (CCF Rank A)

  • Tan Yue, Rui Mao, Xuzhao Shi, Shuo Zhan, Zuhao Yang, Dongyan Zhao: QAEval: Mixture of Evaluators for Question-Answering Task Evaluation. ACL (1) 2025: 14717-14730 (CCF Rank A)

  • Mingxu Tao, Jie Hu, Mingchuan Yang, Yunhuai Liu, Dongyan Zhao, Yansong Feng: EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding. ACL (Findings) 2025: 14874-14885

  • Yiduo Guo, Jie Fu, Huishuai Zhang, Dongyan Zhao: Efficient Domain Continual pretraining by Mitigating the Stability Gap. ACL (1) 2025: 32850-32870 (CCF Rank A)

  • Yuxuan Wang, Yueqian Wang, Bo Chen, Tong Wu, Dongyan Zhao, Zilong Zheng: OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts. CVPR 2025: 18925-18935 (CCF Rank A)

  • Jianxin Liang, Xiaojun Meng, Huishuai Zhang, Yueqian Wang, Jiansheng Wei, Dongyan Zhao: ReasVQA: Advancing VideoQA with Imperfect Reasoning Process. NAACL (Long Papers) 2025: 1696-1709

  • Xiaoxi Sun, Jinpeng Li, Yan Zhong, Dongyan Zhao, Rui Yan: Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework. ICASSP 2025: 1-5

  • Zhen Li, Xinchi Li, Chongyang Tao, Jiazhan Feng, Tao Shen, Can Xu, Hao Wang, Dongyan Zhao, Shuai Ma: RetriEVAL: Evaluating Text Generation with Contextualized Lexical Match. WSDM 2025: 934-943

  • Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Qun Liu, Dongyan Zhao: Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding. AAAI 2025: 25425-25433 (CCF Rank A)

  • Zhenyu Zhang, Bingguang Hao, Jinpeng Li, Zekai Zhang, Dongyan Zhao: E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models. COLING 2025: 2329-2339

  • Mingxu Tao, Dongyan Zhao, Yansong Feng:  Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering, COLING 2025: 11070-11085.

  • Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, Dongyan Zhao: xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. NuerIPS 2024 (CCF Rank A)

  • Jinpeng Li, Yuhan Chen, Pengfei Wu, Yingce Xia, Shufang Xie, Dongyan Zhao, Rui Yan: Learning to Generate Style-Specific Adapters for Stylized Dialogue Generation. NLPCC (1) 2024: 16-28

  • Pengfei Wu, Jiahao Liu, Zhuocheng Gong, Qifan Wang, Jinpeng Li, Jingang Wang, Xunliang Cai, Dongyan Zhao: FIRP: Faster LLM Inference via Future Intermediate Representation Prediction. NLPCC (3) 2024: 158-169

  • Mingxu Tao, Chen Zhang, Quzhe Huang, Tianyao Ma, Songfang Huang, Dongyan Zhao, Yansong Feng: Unlocking the Potential of Model Merging for Low-Resource Languages. EMNLP (Findings) 2024: 8705-8720

  • Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang, Dongyan Zhao, Yang Liu, Zilong Zheng: Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge. EMNLP 2024: 9972-9987

  • Yiduo Guo, Yaobo Liang, Chenfei Wu, Wenshan Wu, Dongyan Zhao, Nan Duan: Learning to Plan by Updating Natural Language. EMNLP (Findings) 2024: 10062-10098

  • Zekai Zhang, Yiduo Guo, Yaobo Liang, Dongyan Zhao, Nan Duan: PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion. EMNLP (Findings) 2024: 12387-12402

  • Zhuocheng Gong, Ang Lv, Jian Guan, Wei Wu, Huishuai Zhang, Minlie Huang, Dongyan Zhao, Rui Yan: Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules. EMNLP 2024: 20924-20938

  • Zhaopeng Xu, Qi Qin, Bing Liu, Dongyan Zhao: Disentangled Representations for Continual Learning: Overcoming Forgetting and Facilitating Knowledge Transfer. ECML/PKDD (4) 2024: 143-159

  • Jinpeng Li, Jiaze Chen, Huadong Chen, Dongyan Zhao, Rui Yan: Multilingual Generation in Abstractive Summarization: A Comparative Study. LREC/COLING 2024: 11827-11837

  • Jinpeng Li, Zekai Zhang, Quan Tu, Xin Cheng, Dongyan Zhao, Rui Yan: StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation. LREC/COLING 2024

  • Mingxu Tao, Quzhe Huang, Kun Xu, Liwei Chen, Yansong Feng, Dongyan Zhao: Probing Multimodal Large Language Models for Global and Local Semantic Representations. LREC/COLING 2024: 13050-13056

  • Haowei Du, Chen Li, Dinghao Zhang, Dongyan Zhao: Bi-Directional Multi-Granularity Generation Framework for Knowledge Graph-to-Text, ACL 2024 (Short): 147-152

  • Jiazhan Feng, Chongyang Tao, Xiubo Geng, Tao Shen, Can Xu, Guodong Long, Dongyan Zhao, Daxin Jiang: Synergistic Interplay between Search and Large Language Models for Information Retrieval, ACL 2024: 9571-9583 (CCF Rank A)

  • Yiduo Guo, Zekai Zhang, Yaobo Liang, Dongyan Zhao, Nan Duan: PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion, ACL (Findings) 2024: 8682-8701

  • Yiduo Guo, Yaobo Liang, Dongyan Zhao, Nan Duan: Large Language Models Can Learn Representation in Natural Language, ACL (Findings) 2024: 9145-9154

  • Zhuocheng Gong, Jiahao Liu, Ziyue Wang, Pengfei Wu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan: Graph-Structured Speculative Decoding, ACL (Findings) 2024: 11404-11415

  • Xin Cheng, Xun Wang, Tao Ge, Si-Qing Chen, Furu Wei, Dongyan Zhao, Rui Yan: SCALE: Synergized Collaboration of Asymmetric Language Translation Engines, ACL (Findings) 2024: 15903-15918

  • Jiazhan Feng, Ruochen Xu, Junheng Hao, Hiteshi Sharma, Yelong Shen, Dongyan Zhao, Weizhu Chen: Language Models can be Deductive Solvers. NAACL-HLT (Findings) 2024: 4026-4042

  • Yueqian Wang, Yuxuan Wang, Kai Chen, Dongyan Zhao: STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering. AAAI 2024: 19215-19223 (CCF Rank A)

  • Zhuocheng Gong, Jiahao Liu, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan: What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation. AAAI 2024: 18082-18089 (CCF Rank A)

  • Zhuocheng Gong, Yang Song, Tao Zhang, Ji-Rong Wen, Dongyan Zhao, Rui Yan: Your Career Path Matters in Person-Job Fit. AAAI 2024: 8427-8435 (CCF Rank A)

  • Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, Rui Yan: Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory. NeurIPS 2023 (CCF Rank A)

  • Haowei Du, Dinghao Zhang, Chen Li, Yang Li, Dongyan Zhao: Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting. EMNLP (Findings) 2023: 2576-2581

  • Chang Liu, Chongyang Tao, Jianxin Liang, Jiazhan Feng, Tao Shen, Quzhe Huang, Dongyan Zhao: Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning. EMNLP (Findings) 2023: 4452-4463

  • Quzhe Huang, Yanxi Zhang, Dongyan Zhao: From Simple to Complex: A Progressive Framework for Document-level Informative Argument Extraction. EMNLP (Findings) 2023: 6129-6140

  • Jinpeng Li, Zekai Zhang, Xiuying Chen, Dongyan Zhao, Rui Yan: Stylized Dialogue Generation with Feature-Guided Knowledge Augmentation. EMNLP (Findings) 2023: 7144-7157

  • Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Ran Wang, Rui Yan: Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression. EMNLP (Findings) 2023: 8643-8657

  • Haowei Du, Quzhe Huang, Chen Li, Chen Zhang, Yang Li, Dongyan Zhao: Relation-Aware Question Answering for Heterogeneous Knowledge Graphs. EMNLP (Findings) 2023: 13582-13592

  • Tianyi Liu, Yansong Feng, Dongyan Zhao: Learning Dynamic Representations for Discourse Dependency Parsing. EMNLP (Findings) 2023: 14253-14263

  • Zhuocheng Gong, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Rui Yan: Improving Input-label Mapping with Demonstration Replay for In-context Learning. EMNLP (Findings) 2023: 14923-14934

  • Mingxu Tao, Yansong Feng, Dongyan Zhao: A Frustratingly Easy Improvement for Position Embeddings via Random Padding. NLPCC (2) 2023: 301-313

  • Yueqian Wang, Yuxuan Wang, Dongyan Zhao: Overview of the NLPCC 2023 Shared Task 10: Learn to Watch TV: Multimodal Dialogue Understanding and Response Generation. NLPCC (3) 2023: 412-419

  • Jiazhan Feng, Chongyang Tao, Tao Shen, Chang Liu, Dongyan Zhao: Dimension-Prompts Boost Commonsense Consolidation. SIGIR 2023: 1934-1938

  • Yuting Wu, Yutong Hu, Yansong Feng, Tianyi Li, Mark Steedman, Dongyan Zhao: Align-then-Enhance: Multilingual Entailment Graph Enhancement with Soft Predicate Alignment. ACL (Findings) 2023: 881-894

  • Yuxuan Wang, Jack Wang, Dongyan Zhao, Zilong Zheng: Rethinking Dictionaries and Glyphs for Chinese Language Pre-training. ACL (Findings) 2023: 1089-1101

  • Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu: Class-Incremental Learning based on Label Generation. ACL (2) 2023: 1263-1276 (CCF Rank A)

  • Zhen Li, Chongyang Tao, Jiazhan Feng, Tao Shen, Dongyan Zhao, Xiubo Geng, Daxin Jiang: FAA: Fine-grained Attention Alignment for Cascade Document Ranking. ACL (1) 2023: 1688-1700 (CCF Rank A)

  • Zhibin Chen, Yansong Feng, Dongyan Zhao: From the One, Judge of the Whole: Typed Entailment Graph Construction with Predicate Generation. ACL (1) 2023: 3534-3551 (CCF Rank A)

  • Yiduo Guo, Yaobo Liang, Dongyan Zhao, Bing Liu, Nan Duan: Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast. ACL (1) 2023: 4002-4017 (CCF Rank A)

  • Yuxuan Wang, Zilong Zheng, Xueliang Zhao, Jinpeng Li, Yueqian Wang, Dongyan Zhao: VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions. ACL (1) 2023: 5036-5048 (CCF Rank A)

  • Chen Zhang, Jiuheng Lin, Xiao Liu, Yuxuan Lai, Yansong Feng, Dongyan Zhao: How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension. ACL (Findings) 2023: 5811-5827

  • Haowei Du, Yansong Feng, Chen Li, Yang Li, Yunshi Lan, Dongyan Zhao: Structure-Discourse Hierarchical Graph for Conditional Question Answering on Long Documents. ACL (Findings) 2023: 6282-6293

  • Jianxin Liang, Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao: Attend, Select and Eliminate: Accelerating Multi-turn Response Selection with Dual-attention-based Content Elimination. ACL (Findings) 2023: 6758-6770

  • Hejing Cao, Dongyan Zhao: Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction. ACL (Findings) 2023: 7180-7188

  • Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, Qingwei Lin: MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation. ACL (1) 2023: 7348-7363 (CCF Rank A)

  • Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan: PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models. ACL (Findings) 2023: 8065-8079

  • Xiao Liu, Da Yin, Chen Zhang, Yansong Feng, Dongyan Zhao: The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code. ACL (Findings) 2023: 9009-9022

  • Quzhe Huang, Yutong Hu, Shengqi Zhu, Yansong Feng, Chang Liu, Dongyan Zhao: More than Classification: A Unified Framework for Event Temporal Relation Extraction. ACL (1) 2023: 9631-9646  (CCF Rank A)

  • Chenshuo Wang, Shaoguang Mao, Tao Ge, Wenshan Wu, Xun Wang, Yan Xia, Jonathan Tien, Dongyan Zhao: Smart Word Suggestions for Writing Assistance. ACL (Findings) 2023: 11212-11225

  • Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan: RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank. ACL (1) 2023: 13785-13802 (CCF Rank A)

  • Shen Gao, Xin Cheng, Mingzhe Li, Xiuying Chen, Jinpeng Li, Dongyan Zhao, Rui Yan: Dialogue Summarization with Static-Dynamic Structure Fusion Graph. ACL (1) 2023: 13858-13873 (CCF Rank A)

  • Xin Cheng, Yankai Lin, Xiuying Chen, Dongyan Zhao, Rui Yan: Decouple knowledge from paramters for plug-and-play language modeling. ACL (Findings) 2023: 14288-14308

  • Yiduo Guo, Bing Liu, Dongyan Zhao: Dealing with Cross-Task Class Discrimination in Online Continual Learning. CVPR 2023: 11878-11887 (CCF Rank A)

  • Zhenni Wang, Xiaohan Yu, Yansong Feng, Dongyan Zhao: An Intra-Class Relation Guided Approach for Code Comment Generation. EACL (Findings) 2023: 1291-1303

  • Chen Zhang, Yuxuan Lai, Yansong Feng, Xingyu Shen, Haowei Du, Dongyan Zhao: Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension. EACL (Findings) 2023: 2394-2407

  • Mingxu Tao, Yansong Feng, Dongyan Zhao: Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study. ICLR 2023

  • Mingzhe Li, Xiuying Chen, Weiheng Liao, Yang Song, Tao Zhang, Dongyan Zhao, Rui Yan: EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator. WSDM 2023: 1102-1110

  • Jinpeng Li, Yingce Xia, Xin Cheng, Dongyan Zhao, Rui Yan: Learning Disentangled Representation via Domain Adaptation for Dialogue Summarization. WWW 2023: 1693-1702 (CCF Rank A)

  • Yuxuan Wang, Xueliang Zhao, Dongyan Zhao: Overview of the NLPCC 2022 Shared Task: Multi-modal Dialogue Understanding and Generation. NLPCC (2) 2022: 328-335

  • Wentao Qin, Dongyan Zhao: Retrieval, Selection and Writing: A Three-Stage Knowledge Grounded Storytelling Model. NLPCC (1) 2022: 352-363

  • Xueliang Zhao, Tingchen Fu, Chongyang Tao, Wei Wu, Dongyan Zhao*, Rui Yan*: Learning to Express in Knowledge-Grounded Conversation. NAACL-HLT 2022: 2258-2273

  • Haowei Du, Quzhe Huang, Chen Zhang, Dongyan Zhao: Knowledge-Enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering. NLPCC (1) 2022: 431-444

  • Zhen Li, Jiazhan Feng, Chongyang Tao, Dongyan Zhao: Training Two-Stage Knowledge-Grounded Dialogues with Attention Feedback. NLPCC (1) 2022: 473-484

  • Yiduo Guo, Bing Liu, Dongyan Zhao: Online Continual Learning through Mutual Information Maximization. ICML 2022: 8109-8126 (CCF Rank A)

  • Jiazhan Feng, Chongyang Tao, Zhen Li, Chang Liu, Tao Shen, Dongyan Zhao Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations. COLING 2022: 389-399

  • Shen Gao, Haotong Zhang, Xiuying Chen, Rui Yan, Dongyan Zhao: Summarizing Procedural Text: Data and Approach. EMNLP (Findings) 2022: 2216-2225

  • Xin Cheng, Shen Gao, Lemao Liu, Dongyan Zhao, Rui Yan: Neural Machine Translation with Contrastive Translation Memories. EMNLP 2022: 3591-3601

  • Zhenwei An, Quzhe Huang, Cong Jiang, Yansong Feng, Dongyan Zhao: Do Charge Prediction Models Learn Legal Theory? EMNLP (Findings) 2022: 3757-3768

  • Xueliang Zhao, Yuxuan Wang, Chongyang Tao, Chenshuo Wang, Dongyan Zhao: Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation. EMNLP (Findings) 2022: 5988-5998

  • Yueqian Wang, Chang Liu, Kai Chen, Xi Wang, Dongyan Zhao: SMASH: Improving SMAll Language Models' Few-SHot Ability with Prompt-Based Distillation. EMNLP (Findings) 2022: 6608-6619

  • Jiazhan Feng, Chongyang Tao, Chang Liu, Rui Yan, Dongyan Zhao: How to Represent Context Better? An Empirical Study on Context Modeling for Multi-turn Response Selection. EMNLP (Findings) 2022: 7285-7298

  • Xiao Liu, Yansong Feng, Jizhi Tang, Chengang Hu, Dongyan Zhao: Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario. EMNLP 2022: 7354-7370

  • Xueliang Zhao, Lemao Liu, Tingchen Fu, Shuming Shi, Dongyan Zhao, Rui Yan: Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure. EMNLP 2022: 10051-10063

  • Chang Liu, Chongyang Tao, Jianxin Liang, Tao Shen, Jiazhan Feng, Quzhe Huang, Dongyan Zhao: Rethinking Task-Specific Knowledge Distillation: Contextualized Corpus as Better Textbook. EMNLP 2022: 10652-10658

  • Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, Rui Yan: GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Passage Retrieval. EMNLP (Findings) 2022: 564-575

  • Chang Liu, Xu Tan, Chongyang Tao, Zhenxin Fu, Dongyan Zhao, Tie-Yan Liu, Rui Yan: ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation. ACL (1) 2022: 962-973 (CCF Rank A)

  • Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao: Multi-Granularity Structural Knowledge Distillation for Language Model Compression. ACL (1) 2022: 1001-1011 (CCF Rank A)

  • Zhuocheng Gong, Di He, Yelong Shen, Tie-Yan Liu, Weizhu Chen, Dongyan Zhao, Ji-Rong Wen, Rui Yan: Finding the Dominant Winning Ticket in Pre-Trained Language Models. ACL (Findings) 2022: 1459-1472

  • Xiao Liu, Da Yin, Yansong Feng, Dongyan Zhao: Things not Written in Text: Exploring Spatial Commonsense from Visual Signals. ACL (1) 2022: 2365-2376 (CCF Rank A)

  • Mingzhe Li, Xiexiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan: Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation. ACL (1) 2022: 4432-4441 (CCF Rank A)

  • Zhibin Chen, Yansong Feng, Dongyan Zhao: Entailment Graph Learning with Textual Entailment and Soft Transitivity. ACL (1) 2022: 5899-5910 (CCF Rank A)

  • Quzhe Huang, Shibo Hao, Yuan Ye, Shengqi Zhu, Yansong Feng, Dongyan Zhao: Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED. ACL (1) 2022: 6241-6252 (CCF Rank A)

  • Shen Gao, Yuchi Zhang, Yongliang Wang, Yang Dong, Xiuying Chen, Dongyan Zhao, Rui Yan: HeteroQA: Learning towards Question-and-Answering through Multiple Information Sources via Heterogeneous Graph Modeling. WSDM 2022: 307-315

  • Yiduo Guo, Wenpeng Hu, Dongyan Zhao, Bing Liu, Adaptive Orthogonal Projection for Batch and Online Continual Learning, AAAI 2022 (2): 6783-6791 (CCF Rank A)

  • Qingqing Zhu, Pengfei Wu, Zhouxing Tan, Jiaxin Duan, Dongyan Zhao, Junfei Liu: Knowledge Distillation with Metric Learning for Medical Dialogue Generation. BIBM 2021: 625-632

  • Qingqing Zhu, Zhouxing Tan, Jiaxin Duan, Pengfei Wu, Dongyan Zhao, Junfei Liu: Dynamic Curriculum Learning with Co-training for Medical Dialogue Generation. BIBM 2021: 633-640

  • Qingqing Zhu, Pengfei Wu, Xiwei Wang, Dongyan Zhao, Junfei Liu: Bidirectional Distillation for Multi-Guidance Medical Dialogue Generation. BIBM 2021: 3185-3192

  • Qi Qin, Wenpeng Hu, Han Peng, Dongyan Zhao, Bing Liu: BNS: Building Network Structures Dynamically for Continual Learning. NeurIPS 2021: 20608-20620 (CCF Rank A)

  • Jinpeng Li, Yingce Xia, Rui Yan, Hongda Sun, Dongyan Zhao, Tie-Yan Liu: Stylized Dialogue Generation with Multi-Pass Dual Learning. NeurIPS 2021: 28470-28481 (CCF Rank A)

  • Qingqing Zhu, Xiuying Chen, Pengfei Wu, JunFei Liu, Dongyan Zhao: Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation. EMNLP (Findings) 2021: 1284-1295

  • Chen Zhang, Yuxuan Lai, Yansong Feng, Dongyan Zhao: Extract, Integrate, Compete: Towards Verification Style Reading Comprehension. EMNLP (Findings) 2021: 2976-2986

  • Zhibin Chen, Yuting Wu, Yansong Feng, Dongyan Zhao: Integrating Manifold Knowledge for Global Entity Linking with Heterogeneous Graphs. CCKS 2021: 91-103

  • Wentao Qin, Dongyan Zhao: Background Semantic Information Improves Verbal Metaphor Identification. NLPCC (2) 2021: 288-300

  • Wentao Qin, Dongyan Zhao: Enhancing Model Robustness via Lexical Distilling. NLPCC (2) 2021: 337-344

  • Haowei Du, Jizhi Tang, Dongyan Zhao: Sentence Ordering by Context-Enhanced Pairwise Comparison. NLPCC (1) 2021: 676-687

  • Quzhe Huang, Shengqi Zhu, Yansong Feng, Yuan Ye, Yuxuan Lai, Dongyan Zhao: Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction. ACL/IJCNLP (2) 2021: 998-1004  (CCF Rank A)

  • Quzhe Huang, Shengqi Zhu, Yansong Feng, Dongyan Zhao: Exploring Distantly-Labeled Rationales in Neural Network Models. ACL/IJCNLP (1) 2021: 5571-5582  (CCF Rank A)

  • Xiuying Chen, Hind Alamro, Mingzhe Li, Shen Gao, Xiangliang Zhang, Dongyan Zhao, Rui Yan: Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation. ACL/IJCNLP (1) 2021: 6068-6077  (CCF Rank A)

  • Yuxuan Lai, Chen Zhang, Yansong Feng, Quzhe Huang, Dongyan Zhao: Why Machine Reading Comprehension Models Learn Shortcuts? ACL/IJCNLP (Findings) 2021: 989-1002

  • Shen Gao, Xiuying Chen, Chang Liu, Dongyan Zhao, Rui Yan: BioGen: Generating Biography Summary under Table Guidance on Wikipedia. ACL/IJCNLP (Findings) 2021: 4752-4757

  • Zhangming Chan, Lemao Liu, Juntao Li, Haisong Zhang, Dongyan Zhao, Shuming Shi, Rui Yan: Enhancing the Open-Domain Dialogue Evaluation in Latent Space. ACL/IJCNLP (Findings) 2021: 4889-4900

  • Chongyang Tao, Shen Gao, Juntao Li, Yansong Feng, Dongyan Zhao, Rui Yan: Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study. NAACL-HLT 2021: 1682-1691

  • Yuxuan Lai, Yijia Liu, Yansong Feng, Songfang Huang, Dongyan Zhao: Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models. NAACL-HLT 2021: 1716-1731

  • Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao: Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis. NAACL-HLT 2021: 1928-1941

  • Rui Yan, Weiheng Liao, Jianwei Cui, Hailei Zhang, Yichuan Hu, Dongyan Zhao: Multilingual COVID-QA: Learning towards Global Information Sharing via Web Question Answering in Multiple Languages. WWW 2021: 2590-2600  (CCF Rank A)

  • Mingfei Guo, Xiuying Chen, Juntao Li, Dongyan Zhao, Rui Yan: How does Truth Evolve into Fake News? An Empirical Study of Fake News Evolution. WWW (Companion Volume) 2021: 407-411  (CCF Rank A)

  • Meng-Hsuan Yu, Juntao Li, Zhangming Chan, Rui Yan, Dongyan Zhao: Content Learning with Structure-Aware Writing: A Graph-Infused Dual Conditional Variational Autoencoder for Automatic Storytelling. AAAI 2021: 6021-6029  (CCF Rank A)

  • Wenpeng Hu, Ran Le, Bing Liu, Feng Ji, Jinwen Ma, Dongyan Zhao, Rui Yan: Predictive Adversarial Learning from Positive and Unlabeled Data. AAAI 2021: 7806-7814  (CCF Rank A)

  • Xiuying Chen, Zhi Cui, Jiayi Zhang, Chen Wei, Jianwei Cui, Bin Wang, Dongyan Zhao, Rui Yan: Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension. AAAI 2021: 12683-12691 (CCF Rank A)

  • Mingzhe Li, Xiuying Chen, Min Yang, Shen Gao, Dongyan Zhao, Rui Yan: The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement. AAAI 2021: 13252-13260 (CCF Rank A)

  • Ruijian Xu, Chongyang Tao, Daxin Jiang, Xueliang Zhao, Dongyan Zhao, Rui Yan: Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues. AAAI 2021: 14158-14166 (CCF Rank A)

主要授权专利


  • 一种基于序列标注模型的学科术语抽取方法及系统，发明专利，中国，ZL201510145663.7，


  • 一种知识点关联方法及系统，发明专利，中国，ZL 201510145575.7


  • 一种基于本体结构的个性化推荐方法，发明专利，中国，ZL201310082157


  • 一种基于外存的图数据存储方法及子图查询方法，发明专利，中国，ZL201110202697.7


  • 一种大规模数据集上的关系查询方法，发明专利，中国，ZL201110259125.2


  • 一种图上两点间最短路径查询方法，发明专利，中国，ZL201110421889.7


  • 电子文件的显示方法及装置，发明专利，中国，ZL200910242121.6


  • 一种检索方法及检索装置，发明专利，中国，ZL200910237186.1


  • 一种对检索结果进行后续处理的方法及装置，发明专利，中国，ZL200910217514.1


  • 一种索引建立方法及装置，发明专利，中国，ZL200910241774.2


  • 一种网站更新实时发布的方法及系统，发明专利，中国，ZL200810247076.9


  • 一种基于序列标注模型的学科术语抽取方法及系统，发明专利，中国，ZL201510145663.7


  • 一种知识点关联方法及系统，发明专利，中国，ZL 201510145575.7


  • 一种基于本体结构的个性化推荐方法，发明专利，中国，ZL201310082157


  • 一种基于外存的图数据存储方法及子图查询方法，发明专利，中国，ZL201110202697.7


  • 一种大规模数据集上的关系查询方法，发明专利，中国，ZL201110259125.2


  • 一种图上两点间最短路径查询方法，发明专利，中国，ZL201110421889.7


  • 电子文件的显示方法及装置，发明专利，中国，ZL200910242121.6


  • 一种检索方法及检索装置，发明专利，中国，ZL200910237186.1


  • 一种对检索结果进行后续处理的方法及装置，发明专利，中国，ZL200910217514.1


  • 一种索引建立方法及装置，发明专利，中国，ZL200910241774.2


  • 一种网站更新实时发布的方法及系统，发明专利，中国，ZL200810247076.9

主要奖励


  • 2006年度国家科技进步二等奖（排名第一）


  • 2005年度北京市科学技术一等奖（排名第一）


  • 第十届中国青年科技奖 


  • 2012年获得国务院政府特殊津贴