赵东岩English

北京大学王选计算机研究所研究员,博士生导师。毕业于北京大学计算机应用技术专业,博士学位。

 

北京大学王选计算机研究所研究员,博士生导师。1987年进入北京大学计算机系本科学习,19911994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。计算机学会(CCF)杰出会员,CCF中文信息技术专委会秘书长、CCF大数据专家委员会委员、CCF网络与数据通信专委会委员,中文信息学会社会媒体处理专委会常委全国新闻出版信息标准化技术委员会委员,全国中文新闻信息标准化技术委员会委员。

近年来承担国家自然科学基金、863、科技支撑计划等国家级项目15项、主持7项,省部级科研项目8项、主持4项,发表学术论文100余篇(包括ACL、AAAI、IJCAI、SIGKDD、SIGIR、SIGMOD、VLDB,AI Journal、TKDE、VLDB Journal等顶级会议和期刊40余篇),授权发明专利20项、申请10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具有自动扩展和质量控制功能的开放域语义知识库构建技术、基于知识库的语义理解与自然语言问答、语义搜索引擎等一系列自然语言理解与认知智能的前沿技术,并开展了面向智能知识服务的行业应用。采用上述技术构建的PKUBase是国内科研单位建设最早且规模最大的语义知识库之一。基于知识库的语义理解和自然语言问答系统在欧盟组织的国际权威评测QALD上连续三年取得了第一名的成绩,在美国NIST组织的TREC微博检索任务上连续两年取得第一名。

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NLPCCCCF 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成为CCF推荐的C类会议。

 

近3年发表的主要文章

  Refereed Journal Papers:

  • Peng Peng, Lei Zou, Lei Chen, Dongyan Zhao: Adaptive Distributed RDF Graph Fragmentation and Allocation based on Query Workload. IEEE Trans. Knowl. Data Eng. 31(4): 670-685 (2019) (CCF Rank A)
  • Liwei Chen, Yansong Feng, Songfang Huang, Bingfeng Luo, Dongyan Zhao: Encoding implicit relation requirements for relation extraction: A joint inference approach,Artificial Intelligence 265: 45-66 (2018) (CCF Rank A)
  • Peng Peng, Lei Zou, Zhenqin Du, Dongyan Zhao: Using partial evaluation in holistic subgraph search. Frontiers Comput. Sci. 12(5): 966-983 (2018)
  • Yanyan Jia, Yansong Feng, Yuan Ye, Chao Lv, Dongyan Zhao, Improve Discourse Parsing with Two-Step Neural Transition-Based Model, ACM Transactions on Asian and Low-Resource Language Information Processing, TALLIP 17(2): 11:1-11:21 (2018)
  • Sen Hu, Lei Zou, Jeffrey Xu Yu, Haixun Wang, Dongyan Zhao: Answering Natural Language Questions by Subgraph Matching over Knowledge Graphs. IEEE Trans. Knowl. Data Eng. TKDE 30(5): 824-837 (2018) (CCF Rank A)
  • Youhuan Li, Lei Zou, Huaming Zhang, Dongyan Zhao: Longest Increasing Subsequence Computation over Streaming Sequences. IEEE Trans. Knowl. Data Eng. TKDE 30(6): 1036-1049 (2018) (CCF Rank A)
  • Tao Chen, Mansheng Li, Qiang He, Lei Zou, Youhuan Li, Cheng Chang, Dongyan Zhao, Yunping Zhu: LiverWiki: a wiki-based database for human liver. BMC Bioinformatics 18(1): 452:1-452:11 (2017)
  • Weiguo Zheng, Lei Zou, Lei Chen, Dongyan Zhao: Efficient SimRank-based Similarity Join, ACM Transactions on Database Systems, TODS 42(3): 16:1-16:37 (2017) (CCF Rank A)
  • Weiguo Zheng, Lei Zou, Xiang Lian, Liang Hong, Dongyan Zhao, Online Subgraph Skyline Analysis Over Knowledge Graphs, TKDE28(7), 2016 (CCF Rank A)
  • Peng Peng, Lei Zou,M. Tamer Özsu, Lei Chen, Dongyan Zhao, Processing SPARQL Queries Over Distributed RDF Graphs, VLDB Journal25(2): 243-268, 2016 (CCF Rank A)
  • Peng Peng, Lei Zou, Lei Chen, Xuemin Lin, Dongyan Zhao: Answering subgraph queries over massive disk resident graphs. World Wide Web J. 19(3): 417-448, 2016

 

  Referred Conference Papers:

  • Chongyang Tao, Wei Wu, Can Xu, Wenpeng Hu, Dongyan Zhao, Rui Yan: Multi-Representation Fusion Network for Multi-Turn Response Selection in Retrieval-Based Chatbots. WSDM 2019: 267-275
  • Shen Gao, Zhaochun Ren, Yihong Zhao, Dongyan Zhao, Dawei Yin, Rui Yan: Product-Aware Answer Generation in E-Commerce Question-Answering. WSDM 2019: 429-437
  • Yuxuan Lai, Yansong Feng, Xiaohan Yu, Zheng Wang, Kun Xu, Dongyan Zhao:Lattice CNNs for Matching Based Chinese Question Answering. AAAI 2019. (CCF Rank A)
  • Shen Gao, Zhaochun Ren, Yihong Eric Zhao, Dongyan Zhao, Dawei Yin, Rui Yan: Product-Aware Answer Generation in E-Commerce Question-Answering. AAAI 2019(CCF Rank A)
  • Juntao Li, Lisong Qiu, Bo Tang, Dongmin Chen, Dongyan Zhao, Rui Yan: Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation.  AAAI 2019(CCF Rank A)
  • Lili  Yao,  Nanyun  Peng,  Ralph  Weischedel,  Kevin  Knight,  Dongyan   Zhao,  Rui  Yan:  Plan-­and-­Write:  Towards  Better  Automatic  Storytelling. AAAI 2019(CCF Rank A)
  • Juntao  Li,  Lidong  Bing,  Lisong  Qiu,  Dongmin  Chen,  Dongyan  Zhao,  Rui   Yan: Learning  to  Write  Stories  with  Thematic  Consistency  and  Wording   Novelty. AAAI 2019(CCF Rank A)
  • Feifan Fan, Yansong Feng, Dongyan Zhao: Multi-grained Attention Network for Aspect-Level Sentiment Classification. EMNLP 2018: 3433-3442
  • Juntao Li, Yan Song, Haisong Zhang, Dongmin Chen, Shuming Shi, Dongyan Zhao, Rui Yan: Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training. EMNLP 2018: 3890-3900
  • Xiuying Chen, Shen Gao, Chongyang Tao, Yan Song, Dongyan Zhao, Rui Yan: Iterative Document Representation Learning Towards Summarization with Polishing. EMNLP 2018: 4088-4097
  • Haisong Zhang, Zhangming Chan, Yan Song, Dongyan Zhao, Rui Yan: When Less Is More: Using Less Context Information to Generate Better Utterances in Group Conversations. NLPCC (1) 2018: 76-84
  • Rui Yan, Dongyan Zhao: Coupled Context Modeling for Deep Chit-Chat: Towards Conversations between Human and Computer. KDD 2018: 2574-2583 (CCF Rank A)
  • Sen Hu, Lei Zou, Jeffrey Xu Yu, Haixun Wang, Dongyan Zhao: Answering Natural Language Questions by Subgraph Matching over Knowledge Graphs (Extended Abstract). ICDE 2018: 1815-1816. (CCF Rank A)
  • Yansong Feng, Songfang Huang, Dongyan Zhao, Rui Yan, Bingfeng Luo, Zheng Wang: Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding. ACL (1) 2018: 2083-2093. (CCF Rank A)
  • Yanyan Jia, Yuan Ye, Yansong Feng, Yuxuan Lai, Rui Yan, Dongyan Zhao: Modeling discourse cohesion for discourse parsing via memory network. ACL (2) 2018: 438-443. (CCF Rank A)
  • Mingyue Shang, Zhenxin Fu, Nanyun Peng, Yansong Feng, Dongyan Zhao, Rui Yan: Learning to Converse with Noisy Data: Generation with Calibration. IJCAI 2018: 4338-4344. (CCF Rank A)
  • Yiping Song, Cheng-Te Li, Jian-Yun Nie, Ming Zhang, Dongyan Zhao, Rui Yan: An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems. IJCAI 2018: 4382-4388. (CCF Rank A)
  • Chongyang Tao, Shen Gao, Mingyue Shang, Wei Wu, Dongyan Zhao, Rui Yan: Get The Point of My Utterance! Learning Towards Effective Responses with Multi-Head Attention Mechanism. IJCAI 2018: 4418-4424 (CCF Rank A)
  • Xiaowei Tong, Zhenxin Fu, Mingyue Shang, Dongyan Zhao, Rui Yan: One "Ruler" for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning. IJCAI 2018: 4432-4438. (CCF Rank A)
  • Rui Yan, Dongyan Zhao: Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm. IJCAI 2018: 4525-4531. (CCF Rank A)
  • Peng Peng, Lei Zou, M. Tamer Özsu, Dongyan Zhao: Multi-query Optimization in Federated RDF Systems. DASFAA (1) 2018: 745-765. (Best Paper)
  • Rui Yan, Dongyan Zhao: A NeuRetrieval Model for Human-Computer Conversations. WWW 2018: 305-312(Companion Volume) (CCF Rank A)
  • Ying Zeng, Yansong Feng, Rong Ma, Zheng Wang, Rui Yan, Chongde Shi, Dongyan Zhao, Scale Up Event Extraction Learning via Automatic Training Data Generation, AAAI 2018: pp6045-6052. (CCF Rank A)
  • Chongyang Tao, Lili Mou, Dongyan Zhao, Rui Yan. RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems, AAAI 2018: pp722-729. (CCF Rank A)
  • Zhenxin Fu, Xiaoye Tan, Nanyun Peng, Dongyan Zhao, Rui Yan. Style Transfer in Text: Exploration and Evaluation, AAAI 2018: pp663-670. (CCF Rank A)
  • Yiping Song, Rui Yan, Yansong Feng, Yaoyuan Zhang, Dongyan Zhao, Ming Zhang. Towards a Neural Conversation Model with Diversity Net Using Determinantal Point Processes. AAAI 2018: pp 5932-5939. (CCF Rank A)
  • Yiping Song, Dongyan Zhao, Ming Zhang, Rui Yan. Diversifying Neural Conversation Model with Maximal Marginal Relevance. IJCNLP(2) 2017: 169-174
  • Jizhi Tang, Chao Lv, Lili Yao, Dongyan Zhao: PKUICST at TREC 2017 Real-Time Summarization Track: Push Notifications and Email Digest. TREC 2017
  • Ying Zeng, Yansong Feng, Dongyan Zhao: WIP Event Detection System at TAC KBP 2017 Event Nugget Track. TAC 2017
  • Xinyi Lin, Rui Yan, Dongyan Zhao. A Hybrid Optimization Framework Fusing Word- and Sentence-Level Information for Extractive Summarization. NLPCC 2017: 124-135
  • Shuo Han, Lei Zou, Jeffrey Xu Yu, Dongyan Zhao: Keyword Search on RDF Graphs - A Query Graph Assembly Approach. CIKM 2017: 227-236
  • Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao and Rui Yan. Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems. EMNLP 2017: 2190-2199
  • Bingfeng Luo, Yansong Feng, Jianbo Xu, Xiang Zhang and Dongyan Zhao, Learning to Predict Charges for Criminal Cases with Legal Basis, EMNLP 2017: 2727-2736
  • Rui Yan, Dongyan Zhao, Weinan E, Joint Learning of Response Ranking and Next Utterance Suggestion in Human-Computer Conversation System, SIGIR 2017: 685-694 (CCF Rank A)
  • Bingfeng Luo, Yansong Feng, Zheng Wang, Zhanxing Zhu, Songfang Huang, Rui Yan, Dongyan Zhao, Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix, ACL (1) 2017: 430-439. (CCF Rank A)
  • Zhiliang Tian, Rui Yan, Lili Mou, Yiping Song, Yansong Feng, Dongyan Zhao, How to Make Contexts More Useful? An Empirical Study to Context-Aware Neural Conversation Models, ACL (2) 2017: 231-236. (CCF Rank A)
  • Kun Xu, Yansong Feng, Songfang Huang, Dongyan Zhao, Hybrid Question Answering over Knowledge Base and Free Text, pp. 2397-2407, COLING 2016: 2397-2407
  • Ying Zeng, Honghui Yang, Yansong Feng, Dongyan Zhao, A Convolution BiLSTM Neural Network Model for Chinese Event Extraction, NLPCC-ICCPOL 2016: 275-287
  • Chao Lv, Lili Yao, Yansong Feng, Dongyan Zhao, Improving Collaborative Filtering with Long-Short Interest Model, NLPCC-ICCPOL 2016: 335-346
  • Bingfeng Luo, Yansong Feng, Zheng Wang, Dongyan Zhao, Improving First Order Temporal Fact Extraction with Unreliable Data, NLPCC-ICCPOL 2016: 251-262
  • Liwei Chen, Yansong Feng, Dongyan Zhao, TDSS: A New Word Sense Representation Framework for Information Retrieval, NLPCC-ICCPOL 2016: 63-75
  • Yanyan Jia, Yansong Feng, Bingfeng Luo, Yuan Ye, Tianyang Liu, Dongyan Zhao, Transition-Based Discourse Parsing with Multilayer Stack Long Short Term Memory, NLPCC-ICCPOL 2016: 360-373
  • Chao Lv, Yansong Feng, Dongyan Zhao, Purchase Prediction via Machine Learning in Mobile Commerce, NLPCC-ICCPOL 2016: 506-513
  • Yuxuan Lai, Yang Lin, Jiahao Chen, Yansong Feng, Dongyan Zhao: Open Domain Question Answering System Based on Knowledge Base. NLPCC/ICCPOL 2016: 722-733
  • Ke Sun, Tingting Li, Shiqi Zhao, Yajuan Lv, Yansong Feng, Xiaojun Wan, Dongyan Zhao: Overview of Baidu Cup 2016: Challenge on Entity Search. NLPCC/ICCPOL 2016: 848-853
  • Zhe Han, Yansong Feng, Dongyan Zhao, Detecting Synonymous Predicates from Online Encyclopedia with Rich Features, The 12th Asia Information Retrieval Societies Conference, AIRS 2016: 111-122
  • Lili Yao, Chao Lv, Feifan Fan, Jianwu Yang, Dongyan Zhao, PKU ICST at TREC 2016 Real-Time Summarization Track: Push Notifications and Email Digest, The 25th Text Retrieval Conference (TREC2016)
  • Ying Zeng, Bingfeng Luo, Yansong Feng, Dongyan Zhao , WIP Event Detection System at TAC KBP 2016 Event Nugget Track, Text Analysis Conference (TAC2016)
  • Feifan Fan, Yansong Feng, Dongyan Zhao, Real-time Filtering on Interest Profiles in Twitter Stream, pp. 1079-1088 , CIKM 2016: 1079-1088
  • Weiguo Zheng, Lei Zou, Dongyan Zhao, Semantic SPARQL Similarity Search Over RDF Knowledge Graphs, VLDB 2016; PVLDB 9(11): 840-851 (2016) (CCF Rank A)
  • Youhuan Li, Lei Zou, Huaming Zhang, Dongyan Zhao: Computing Longest Increasing Subsequences over Sequential Data Streams. VLDB 2016; PVLDB 10(3): 181-192 (2016) (CCF Rank A)
  • Kun Xu, Yansong Feng, Siva Reddy, Songfang Huang, Dongyan Zhao, Question Answering on Freebase via Relation Extraction and Textual Evidence, ACL 2016: 2326-2336 (CCF Rank A)
  • Bingfeng Luo, Yuxuan Lai, Lili Yao, Yansong Feng, Dongyan Zhao, Multi-choice Question Answering System of WIP at NTCIR-12 QA Lab, NTCIR-2016
  • YueFei, Chao Lv, Yansong Feng, Dongyan Zhao, Real-time Filtering on Interest Profiles in Twitter Stream. JCDL 2016: 263-264
  • Lili Yao, Feifan Fan,Yansong Feng, Dongyan Zhao, Leveraging Tweet Ranking in an Optimization Framework. JCDL 2016: 245-246
  • Peng Peng, Lei Zou, Lei Chen, Dongyan Zhao, Query Workload-based RDF Graph Fragmentation and Allocation, EDBT 2016: 377-388

 

主要授权专利

  • 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

第十届中国青年科技奖

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);