基本信息
刘康  男  硕导  中国科学院自动化研究所
电子邮件: kliu@nlpr.ia.ac.cn
通信地址: 北京市海淀区中关村东路95号
邮政编码:
部门/实验室:模式识别国家重点实验室

研究领域

自然语言处理、信息抽取、问答系统、信息检索、机器学习

招生信息

   
招生专业
081203-计算机应用技术
招生方向
自然语言处理,信息抽取,问答系统,信息检索

教育背景

2006-09--2010-07   中国科学院自动化研究所   博士
2002-09--2005-04   西安电子科技大学   硕士
1998-09--2002-07   西安电子科技大学   学士

工作经历

  • 2005-2006 清华同方任高级软件工程师

  • 2010-今  中国科学院自动化研究所模式识别国家重点实验室

科研活动

   
科研项目
( 1 ) 知识关联与推理类问题求解关键技术及系统, 主持, 国家级, 2015-01--2017-12
( 2 ) Representing and Reasoning Knowledge by Jointly Learning on Knowledge Graphs, Textual Triples and Unstructured Texts, 主持, 院级, 2015-10--2016-10
( 3 ) 基于大规模知识图谱的文本语义分析、知识图谱补全与验证, 主持, 院级, 2015-06--2016-06
( 4 ) 跨语言QA系统的研究开发, 主持, 院级, 2015-06--2015-12
( 5 ) 互联网环境下中文实体知识挖掘关键技术研究, 主持, 国家级, 2013-01--2015-12

发表文章

  • Guoliang Ji, Kang Liu, Shizhu He and Jun Zhao, Knowledge Graph Completion with Adaptive Sparse Transfer Matrix, in Proceedings of AAAI 2016, Phoenix, USA, Phoenix, 12-17. 
  • Shulin liu, Kang Liu, Shizhu He and Jun Zhao, A Probabilistic Soft Logic Based Approach to Exploiting Latent and Global Information in Event Classification, in Proceedings of AAAI 2016, Phoenix, USA, Phoenix, 12-17 
  • Yuanzhe Zhang, Shizhu He, Kang Liu and Jun Zhao, A Joint Model for Question Answering over Multiple Knowledge Bases, in Proceedings of AAAI 2016, Phoenix, USA, Phoenix, 12-17。
  • Daojian Zeng, Kang Liu, Yubo Chen and Jun Zhao, Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks, in Proceedings of EMNLP 2015, Lisbon, Portugal, September, 17-21. 
  • Kang Liu, Jun Zhao, Shizhu He and Yuanzhe Zhang, Questiong Answering over Knoweldge Base, a Nature Language Processing Special Issue in IEEE Transaction on Intelligent Systems, pp. 1541-1672.
  • Shizhu He, Kang Liu and Jun Zhao, Learning to Represent Knowledge Graphs with Gaussian Embedding, in Proceedings of CIKM 2015, Melbourne, Astralia, October, 19-23. 
  • Zhuoyu Wei, Jun Zhao, Kang Liu, Zhenyu Qi and Guanhua Tian, Large-scale Knowledge Base Completion: Inferring via Grounding Network Sampling over Selected Instances, in Proceedings of CIKM 2015, Melbourne, Astralia, October, 19-23. 
  • Linlin Wang, Kang Liu, Zhu Cao, Jun Zhao and Gerard de Melo, Sentiment-Aspect Extraction based on Restricted Boltzmann Machines, in Proceedings of ACL-IJCNLP 2015, Beijing, China, July, 26-29. 
  • Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu and Jun Zhao, Knowledge Graph Embedding via Dynamic Mapping Matrix, in Proceedings of ACL-IJCNLP 2015, Beijing, China, July, 26-29. 
  • Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng and Jun Zhao, Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks, in Proceedings of ACL-IJCNLP 2015, Beijing, China, July, 26-29.
  • Siwei Lai, Liheng Xu, Kang Liu and Jun Zhao, Recurrent Convolutional Neural Networks for Text Classification, in Proceedings of AAAI 2015, Austin Texas, USA, January, 25-23. 
  • Shizhu He, Kang Liu, Yuanzhe Zhang and Jun Zhao, Questioning Answering over Linked Data Using Markov First-order Logic, in Proceedings of EMNLP 2014, Doha, Qatar, October, 25-29.
  • Kang Liu, Liheng Xu and Jun Zhao, Co-extracting Opinion Targets and Opinion Words from Online Reviews Based on the Word Alignment Model, IEEE Transaction on Knowledge and Data Engineering (TKDE), VOL. 27, Issue No. 03 pp. 636-650. 
  • Kang Liu, Liheng Xu and Jun Zhao, Extracting Opinion Targets and Opinion Words from Online Reviews with Graph Co-ranking, in Proceedings of ACL 2014, Baltimore, USA, June 22-27. 
  • Liheng Xu, Kang Liu, Siwei Lai and Jun Zhao, Product Feature Mining: Semantic Clues versus Syntactic Constituents, in Proceedings of ACL 2014, Baltimore, USA, June 22-27. 
  • Liheng Xu, Kang Liu and Jun Zhao, Joint Opinion Relation Detection Using One-Class Deep Neural Network, in Proceedings of COLING 2014, Dublin, Ireland, August, 23-29. PDF
  • Daojian Zeng, Kang Liu, Siwei Lai, Guangyou Zhou and Jun Zhao, Relation Classification via Convolutional Deep Neural Network, in Proceedings of COLING 2014, Dublin, Ireland, August, 23-29. Best Paper Award 
  • Yang Liu, Kang Liu, Liheng Xu and Jun Zhao, Exploring Fine-grained Entity Type Constraints for Distantly Supervised Relation Extraction, in Proceedings of COLING 2014, Dublin, Ireland, August, 23-29. 
  • Shizhu He, Yuanzhe Zhang, Kang Liu and Jun Zhao, CASIA@V2: A MLN-based Question Answering System over Linked Data, in Proceedings of the fourth workshop on question answering over linked data (QALD-4) in CLEF 2014, Sheffield, UK, September, 15-18.