基本信息
韩先培  男  博导  中国科学院软件研究所
电子邮件: xianpei@iscas.ac.cn
通信地址: 北京市海淀区中关村南四街4号5号楼1201
邮政编码: 100190

研究领域

个人主页:http://www.icip.org.cn/team/hanxianpei/


大规模知识图谱构建及智能信息服务技术:

Information Integration

  • Named Entity Disambiguation
  • Entity Linking
  • Entity Resolution

Information Extraction/Knowledge Graph

  • Relation Extraction
  • Named Entity Recognition
  • Knowledge Harvesting

Information Retrieval/QA

  • Semantic Search
  • Information Exploitation
  • Question Answering


教育背景

2005-09--2010-07   中国科学院自动化研究所   博士
2001-09--2005-07   北方工业大学   学士

工作经历

   
工作简历
2018-10~现在, 中国科学院软件研究所, 研究员
2012-12~2018-09,中国科学院软件研究所, 副研究员
2010-07~2012-12,中国科学院软件研究所, 助理研究员
社会兼职
2017-09-01-今,中国中文信息学会语言与知识计算专业委员会, 副主任
2016-01-01-今,中国中文信息学会, 理事

出版信息

   
发表论文
[1] Liu, Fangchao, Lin, Hongyu, Han, Xianpei, Cao, Boxi, Sun, Le. Pre-training to Match for Unified Low-shot Relation Extraction. 2022, [2] 陈晓阳, Kai Hui, 何苯, 韩先培, 孙乐, 叶正. Incorporating Ranking Context for End-to-End BERT Re-ranking. ECIR 2022null. 2022, [3] Chen, Jiawei, Liu, Qing, Lin, Hongyu, Han, Xianpei, Sun, Le. Few-shot Named Entity Recognition with Self-describing Networks. ACLnull. 2022, [4] Xu, Ruoxi, Lin, Hongyu, Liao, Meng, Han, Xianpei, Xu, Jin, Tan, Wei, Sun, Yingfei, Sun, Le. ECO v1: Towards Event-Centric Opinion Mining. 2022, [5] Cao, Boxi, Lin, Hongyu, Han, Xianpei, Liu, Fangchao, Sun, Le. Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View. ACLnull. 2022, [6] Lu, Yaojie, Liu, Qing, Dai, Dai, Xiao, Xinyan, Lin, Hongyu, Han, Xianpei, Sun, Le, Wu, Hua. Unified Structure Generation for Universal Information Extraction. ACLnull. 2022, [7] Lu, Yaojie, Lin, Hongyu, Xu, Jin, Han, Xianpei, Tang, Jialong, Li, Annan, Sun, Le, Liao, Meng, Chen, Shaoyi. TEXT2EVENT: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction. ACLnull. 2021, 2795-2806, [8] Zhang, Wenkai, Lin, Hongyu, Han, Xianpei, Sun, Le, Liu, Huidan, Wei, Zhicheng, Yuan, Nicholas Jing. Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model. ACLnull. 2021, http://arxiv.org/abs/2106.09234.
[9] Wu, Shan, Chen, Bo, Xin, Chunlei, Han, Xianpei, Sun, Le, Zhang, Weipeng, Chen, Jiansong, Yang, Fan, Cai, Xunliang. From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding. ACLnull. 2021, http://arxiv.org/abs/2106.06228.
[10] Bian, Ning, Han, Xianpei, Chen, Bo, Sun, Le. Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation. AAAInull. 2021, http://arxiv.org/abs/2101.00760.
[11] Liu, Fangchao, Yan, Lingyong, Lin, Hongyu, Han, Xianpei, Sun, Le. Element Intervention for Open Relation Extraction. ACLnull. 2021, http://arxiv.org/abs/2106.09558.
[12] 韩先培. End-to-End Bootstrapping Neural Network for Entity Set. Thirty-Fourth AAAI Conference on Artificial Intelligence. 2020, [13] 罗威, 罗准辰, 雷帅, 程齐凯, 陆伟, 张瑾, 韩涛, 冯岩松, 韩先培, 冯冲, 张均胜, 刘志辉, 乔林波, 李东升, 许儒红, 陈敬一. 智能科学家--科技信息创新引领的下一代科研范式. 情报理论与实践[J]. 2020, 43(1): 1-5+17, https://kns.cnki.net/KCMS/detail/detail.aspx?dbcode=CJFQ&dbname=CJFDLAST2020&filename=QBLL202001001&v=MjY4ODVyRzRITkhNcm85RlpZUjhlWDFMdXhZUzdEaDFUM3FUcldNMUZyQ1VSN3FmYnVkcEZDcmhWTC9PTkMvSFk=.
[14] 韩先培. Global Structure and Local Semantics-Preserved Embeddings for Entity Alignment. the 29th International Joint Conference on Artificial Intelligence. 2020, [15] 孙乐. Hierarchical Matching Network for Heterogeneous Entity Resolution. the 29th International Joint Conference on Artificial Intelligence. 2020, [16] 孙乐. Learning to Map Frequent Phrases to Sub-Structures of Meaning Representation for Neural Semantic Parsing. Thirty-Fourth AAAI Conference on Artificial Intelligence. 2020, [17] He Ben. End-to-End Bootstrapping Neural Network for Entity Set Expansion. Proc. of AAAI. 2020, [18] 韩先培. Gazetteer-Enhanced Attentive Neural Networks for Named Entity Recognition. 2019 Conference on Empirical Methods in Natural Language Processing. 2019, [19] 陈波, 孙乐, 韩先培. 基于桥连接的词典学习方法的语义解析. 中文信息学报[J]. 2019, 33(5): 24-30, http://lib.cqvip.com/Qikan/Article/Detail?id=7002204750.
[20] 宋希良, 韩先培, 孙乐. 面向新类型人名识别的数据增强方法. 中文信息学报[J]. 2019, 33(6): 72-79, http://lib.cqvip.com/Qikan/Article/Detail?id=7002632102.
[21] 韩先培. Learning to Bootstrap for Entity Set Expansion. 2019 Conference on Empirical Methods in Natural Language Processing. 2019, [22] 陆垚杰, 林鸿宇, 韩先培, 孙乐. 基于语言学扰动的事件检测数据增强方法. 中文信息学报[J]. 2019, 110-117, http://lib.cqvip.com/Qikan/Article/Detail?id=77698383504849574855484952.
[23] Lu Yaojie, Lin Hongyu, Han Xianpei, Sun Le. Distilling Discrimination and Generalization Knowledge for Event Detection via Delta-Representation Learning. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)[J]. 2019, 4366-4376, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493046106088.
[24] Nie, Hao, Han, Xianpei, He, Ben, Sun, Le, Chen, Bo, Zhang, Wei, Wu, Suhui, Kong, Hao, ACM. Deep Sequence-to-Sequence Entity Matching for Heterogeneous Entity Resolution. PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19)null. 2019, 629-638, http://dx.doi.org/10.1145/3357384.3358018.
[25] Lin Hongyu, Lu Yaojie, Han Xianpei, Sun Le, ACL, Korhonen A, Traum D, Marquez L. Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)null. 2019, 5182-5192, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493046107069.
[26] Lin Hongyu, Lu Yaojie, Han Xianpei, Sun Le. Cost-sensitive Regularization for Label Confusion-aware Event Detection. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019)[J]. 2019, 5278-5283, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493046107079.
[27] 孙乐. End-to-End Multi-Perspective Matching for Entity Resolution.. In the 28th International Joint Conference on Artificial Intelligence(IJCAI 2019). 2019, [28] Su, Jinsong, Tang, Jialong, Lu, Ziyao, Han, Xianpei, Zhang, Haiying. A neural image captioning model with caption-to-images semantic constructor. NEUROCOMPUTING[J]. 2019, 367: 144-151, http://dx.doi.org/10.1016/j.neucom.2019.08.012.
[29] 安波, 韩先培, 孙乐. 融合知识表示的知识库问答系统. 中国科学:信息科学[J]. 2018, 48(11): 1521-1532, https://www.sciengine.com/doi/10.1360/N112018-00208.
[30] Chen Bo, Sun Le, Han Xianpei. Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing. PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1[J]. 2018, 766-777, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493904300071.
[31] Lin Hongyu, Lu Yaojie, Han Xianpei, Sun Le. Nugget Proposal Networks for Chinese Event Detection. PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1[J]. 2018, 1565-1574, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493904300145.
[32] 马龙龙, 韩先培, 孙乐. 图像的文本描述方法研究综述. 中文信息学报[J]. 2018, 32(4): 1-12, http://lib.cqvip.com/Qikan/Article/Detail?id=675358828.
[33] 孙乐. Model-Free Context-Aware Word Composition. The 27th International Conference on Computational Linguistics. 2018, [34] 孙乐. Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing. The 27th International Conference on Computational Linguistics. 2018, [35] Liu Yang, Zeng Qingguo, Yang Huanrui, Carrio Adrian, Yoshida K, Lee M. Stock Price Movement Prediction from Financial News with Deep Learning and Knowledge Graph Embedding. KNOWLEDGE MANAGEMENT AND ACQUISITION FOR INTELLIGENT SYSTEMS (PKAW 2018)null. 2018, 11016: 102-113, [36] Lin Hongyu, Lu Yaojie, Han Xianpei, Sun Le, Gurevych I, Miyao Y. Adaptive Scaling for Sparse Detection in Information Extraction. PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1null. 2018, 1033-1043, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493904300095.
[37] 孙乐. Accurate Text-Enhanced Knowledge Graph Representation Learning. The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics. 2018, [38] Han Xianpei, Sun Le. Distant Supervision via Prototype-Based Global Representation Learning. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE[J]. 2017, 3443-3449, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485630703069.
[39] Han Xianpei, Sun Le. Global Distant Supervision for Relation Extraction. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE[J]. 2016, 2950-2956, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485474202138.
[40] 安波, 韩先培, 孙乐, 吴健. 基于分布式表示和多特征融合的知识库三元组分类. 中文信息学报[J]. 2016, 30(6): 84-89,99, http://lib.cqvip.com/Qikan/Article/Detail?id=671314774.
[41] Chen Bo, Sun Le, Han Xianpei, An Bo, Erk K, Smith NA. Sentence Rewriting for Semantic Parsing. PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1null. 2016, 766-777, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493806800073.
[42] 韩先培. Context-Sensitive Inference Rule Discovery: A Graph-Based Method. COLING. 2016, [43] Zhang Zhenzhong, Sun Le, Han Xianpei, AAAI. A Joint Model for Entity Set Expansion and Attribute Extraction from Web Search Queries. THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCEnull. 2016, 3101-3107, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000485474203020.
[44] Zhang Zhenzhong, Sun Le, Han Xianpei. Learning to Mine Query Subtopics from Query Log. PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL) AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (IJCNLP), VOL 2[J]. 2015, 341-345, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493810000056.
[45] Su Jinsong, Xiong Deyi, Liu Yang, Han Xianpei, Lin Hongyu, Yao Junfeng, Zhang Min, Zong C, Strube M. A Context-Aware Topic Model for Statistical Machine Translation. PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1null. 2015, 229-238, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493808900023.
[46] 彭泽环, 孙乐, 韩先培, 陈波. 社区热点微博推荐研究. 计算机研究与发展[J]. 2015, 52(5): 1014-1021, http://lib.cqvip.com/Qikan/Article/Detail?id=664766444.
[47] 张振中, 孙乐, 韩先培. 基于翻译模型的查询会话检测方法研究. 中文信息学报[J]. 2015, 29(4): 95-102, http://lib.cqvip.com/Qikan/Article/Detail?id=666607097.
[48] 韩先培. A Probabilistic Co-Bootstrapping Method for Entity Set Expansion. the 25th International Conference on Computational Linguistics. 2014, [49] Han Xianpei, Sun Le. Semantic consistency: A local subspace based method for distant supervised relation extraction. 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014null. 2014, 718-724, http://ir.iscas.ac.cn/handle/311060/16630.
[50] Sun Le, Han Xianpei. A Feature-Enriched Tree Kernel for Relation Extraction. PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2[J]. 2014, 61-67, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493811100011.
[51] Zhou Guangyou, Liu Kang, Zhao Jun, Han Xianpei, Liu Yang, Qi Zhenyu. Knowledge Extraction from Wiki/BBS/Blogs/News Websites. KNOWLEDGE EXTRACTION FROM WIKI/BBS/BLOGS/NEWS WEBSITES. 2014, http://ir.ia.ac.cn/handle/173211/20674.
[52] Han Xianpei, Sun Le. Semantic Consistency: A Local Subspace Based Method for Distant Supervised Relation Extraction. PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2[J]. 2014, 718-724, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000493811100117.
[53] Sun Le, Han Xianpei. A feature-enriched tree kernel for relation extraction. 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014null. 2014, 61-67, http://ir.iscas.ac.cn/handle/311060/16572.
[54] Zhang Zhenzhong, Sun Le, Han Xianpei. Learning to detect task boundaries of query session. 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013null. 2013, 1885-1888, http://ir.iscas.ac.cn/handle/311060/16649.
[55] 彭泽环, 孙乐, 韩先培, 石贝. 基于排序学习的微博用户推荐. 中文信息学报[J]. 2013, 27(4): 96-102, http://lib.cqvip.com/Qikan/Article/Detail?id=46842386.
[56] 石贝, 孙乐, 韩先培. 基于图的查询日志实体别名抽取方法. 中文信息学报[J]. 2013, 27(5): 149-155, http://lib.cqvip.com/Qikan/Article/Detail?id=47684369.
[57] 张苇如, 孙乐, 韩先培. 基于维基百科和模式聚类的实体关系抽取方法. 中文信息学报[J]. 2012, 26(2): 75-81, http://lib.cqvip.com/Qikan/Article/Detail?id=41328169.
[58] 孙乐. An Entity-Topic Model for Entity Linking. Conference on Empirical Methods in Natural Language Processing and Natural Language Learning. 2012, [59] Han Xianpei, Sun Le. A generative entity-mention model for linking entities with knowledge base. ACL-HLT 2011 - PROCEEDINGS OF THE 49TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIESnull. 2011, 945-954, http://ir.iscas.ac.cn/handle/311060/16282.
[60] 韩先培. ACL HLT 2011会议评述. 中文信息学报[J]. 2011, 25(5): 127-128, http://lib.cqvip.com/Qikan/Article/Detail?id=39487698.
[61] Han Xianpei, Sun Le, Zhao Jun. Collective entity linking in web text: a graph-based method. SIGIR'11 - PROCEEDINGS OF THE 34TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVALnull. 2011, 765-774, http://124.16.136.157/handle/311060/14347.
[62] Han Xianpei, Zhao Jun, Assoc Computat Linguist. Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation. ACL 2010: 48TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICSnull. 2010, 50-59, http://apps.webofknowledge.com/CitedFullRecord.do?product=UA&colName=WOS&SID=5CCFccWmJJRAuMzNPjj&search_mode=CitedFullRecord&isickref=WOS:000391195300006.
[63] Zhao Jun. Topic-driven web search result organization by leveraging Wikipedia semantic knowledge. INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENnull. 2010, 1749-1752, http://ir.ia.ac.cn/handle/173211/4762.
[64] Zhao Jun. Web personal name disambiguation based on reference entity tables mined from the web. INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENnull. 2009, 75-82, http://ir.ia.ac.cn/handle/173211/4763.
[65] 韩先培, 赵军. 基于Wikipedia的语义元数据生成. 中文信息学报[J]. 2009, 23(2): 108-114, http://lib.cqvip.com/Qikan/Article/Detail?id=29776844.
[66] Zhao Jun. Named entity disambiguation by leveraging wikipedia semantic knowledge. INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENnull. 2009, 215-224, http://ir.ia.ac.cn/handle/173211/4759.
[67] 韩先培, 刘康, 赵军. 基于布局特征与语言特征的网页主要内容块发现. 中文信息学报[J]. 2008, 22(1): 15-21, http://lib.cqvip.com/Qikan/Article/Detail?id=26384129.
[68] Han Xianpei, Zhao Jun, Liu Kang. A WebPage Content Block Detection Method Based on Layout Features and Languages Features. CHINESE JOURNAL OF COMPUTERS[J]. 2008, 15-21, http://ir.ia.ac.cn/handle/173211/20665.
[69] Han Xianpei, Liu Kang, Zhao Jun, Wang Gen. NLPR in TREC 2007 Blog Track. 2007, http://ir.ia.ac.cn/handle/173211/20668.

科研活动

   
科研项目
( 1 ) 基于大数据的面向开放域的智能问答技术, 参与, 国家级, 2017-10--2021-09
( 2 ) 基于垂直领域(石油)的知识获取和知识图谱构建项目, 主持, 院级, 2019-05--2020-08
( 3 ) 北京智源研究院自然语言处理重大方向青年科学家, 主持, 研究所(学校), 2019-11--2022-10
参与会议
(1)An Entity-Topic Model for Entity Linking   自然语言处理实证方法会议   韩先培,孙乐   2012-07-15
(2)Collective Entity Linking in Web Text: A Graph-Based Method   国际信息检索大会   Xianpei Han, Le Sun and Jun Zhao   2011-07-24
(3)A Generative Entity-Mention Model for Linking Entities with Knowledge Base   第49届自然语言处理年会   Xianpei Han and Le Sun   2011-06-19
(4)Topic-Driven Web Search Result Organization by Leveraging Wikipedia Semantic Knowledge   第19届国际信息和知识管理大会   Xianpei Han and Jun Zhao   2010-10-26
(5)Structural Semantic Relatedness: A Knowledge-Based Method to Named Entity Disambiguation   第48届自然语言处理年会    Xianpei Han and Jun Zhao   2010-07-11
(6)Named Entity Disambiguation by Leveraging Wikipedia Semantic Knowledge   第18届国际信息和知识管理大会   Xianpei Han and Jun Zhao.   2009-11-02

指导学生

已指导学生

宋希良  硕士研究生  081202-计算机软件与理论  

现指导学生

边宁  硕士研究生  081202-计算机软件与理论  

王天舒  硕士研究生  081202-计算机软件与理论