
何世柱 男 中国科学院自动化研究所
电子邮件: shizhuhe@163.com
通信地址: 北京市海淀区中关村东路95号智能化大厦711
邮政编码: 100190
课题组招收硕博生、工程师、实习生,欢迎联系。
研究领域
招生信息
招生专业
招生方向
问答系统、对话系统、知识推理
自然语言处理、知识图谱、深度学习
教育背景
工作经历
工作简历:
2018.11 - 今,中国科学院自动化研究所,模式识别国家重点实验室,副研究员;
2016.7 - 2018.11,中国科学院自动化研究所,模式识别国家重点实验室,助理研究员;
学术任职:
中国中文信息学会青年工作委员会委员
中国中文信息学会语言与知识计算专业委员会委员
中国中文信息学会医疗健康与生物信息专业委员会委员
授课情况:
(1) 2020-2021年,春季学期,知识图谱,中国科学院大学 (校级优秀课程)
(2) 2019-2020年,春季学期,知识图谱与语义计算,中国科学院大学 (院级优秀课程)
(3) 2018-2019年,春季学期,知识图谱与语义计算,中国科学院大学
(4) 2017-2018年,夏季学期,深度学习下的自然语言处理:理论与实践,中国科学院大学
专利与奖励
获奖情况:
(1) 入选中国科学院青年创新促进会, 院级, 2019
(2) 2019年度北京市科学技术进步奖一等奖(排名第四), 一等奖, 省级, 2019
(3) 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(排名第三), 一等奖, 其他, 2018
(4) 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(排名第七), 一等奖, 其他, 2020
(5) “CCF-腾讯”犀牛鸟基金优秀专利奖, 2019
(6) CCF-腾讯犀牛鸟科研基金奖,2018
(7) CCKS 2019最佳论文, 2019
(8) CCL and NLP-NABD 2016最佳论文奖, 2016
(9) CCIR 2014 ,优秀论文奖, 2014
学术评测:
(1) AAAI 2022中的缩写词抽取与消歧评测比赛冠军(1/55)
(2) 2021未来杯高校AI学术联赛全国总冠军(1/609)
(3) CCKS 2021中的医疗科普知识答非所问识别评测比赛冠军(1/261)
(4) CCKS 2021中的Aminer学者画像评测比赛季军(3/290)
(5) 问答系统国际学术评测CLEF QALD-3自动方法第一名
专利成果:
(1) Method and Device for Parsing Interrogative Sentence in Knowledge Base, 发明, 2015, 第 3 作者, 专利号: 15845782.0– 1952 PCT/CN2015078362.
(2) 基于强化学习的关系抽取方法和装置, 发明, 2018, 第 1 作者, 专利号: 2018100030626
(3) 基于给定事实的问句生成方法与系统, 发明, 2019, 第 2 作者, 专利号: 201911276552.4
(4) 基于信息增强的对话状态跟踪方法、系统、装置, 发明, 2019, 第 2 作者, 专利号: 201911276031.9
出版信息
出版论著
(1)《知识图谱》, 高等教育出版社, 2018-10, 第 3 作者
(2)《知识图谱:算法与实践》, 高等教育出版社, 2022-04, 第 3 作者
发表论文(近五年)
(1)Fangyu Lei, Shizhu He, Xiang Li, Yifan Wei, Yiming Huang, Jun Zhao and Kang Liu. S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering. In Proceedings of ACL 2023.
(2)Yao Xu, Shizhu He, Li Cai, Kang Liu and Jun Zhao. Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural Network. In the Findings of ACL 2023.
(3)Ran Song, Shizhu He, Shengxiang Gao, Li Cai, Kang Liu, Zhengtao Yu and Jun Zhao. Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints. In the Findings of ACL 2023.
(4)Qingbin Liu, Yanchao Hao, Xiaolong Liu, Bo Li, Dianbo Sui, Shizhu He, Kang Liu, Jun Zhao, Xi Chen, Ningyu Zhang and Jiaoyan Chen. Class Lifelong Learning for Intent Detection via Structure Consolidation Networks. In the Findings of ACL 2023.
(5)Tianyu Wu*, Shizhu He*, Jingping Liu*, Siqi Sun, Kang Liu, Qing-Long Han, Yang Tang. A Brief Overview of ChatGPT: The History, Status Quo and Potential Future Development. IEEE/CAA Journal of Automatica Sinica ( Volume: 10, Issue: 5, May 2023).
(6)Guirong Bai, Shizhu He, Kang Liu, Jun Zhao. Bidirectional Sentence Ordering with Interactive Decoding. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) 2023.
(7)Runxin Sun, Shizhu He, Chong Zhu, Yaohan He, Jinlong Li, Jun Zhao, Kang Liu. Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing. In Proceedings of ACL 2022, Dublin, Ireland, May 22-27.
(8)Guirong Bai, Shizhu He, Kang Liu, Jun Zhao. Incremental Intent Detection for Medical Domain with Contrast Replay Networks. In the Findings of ACL 2022, Dublin, Ireland, May 22-27.
(9) Guirong Bai, Qingbin Liu, Shizhu He, Kang Liu, and Jun Zhao. Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision[J]. Journal of Computer Science and Technology, 2022.
(10)Guirong Bai, Shizhu He, Kang Liu, and Jun Zhao. Example-guided stylized response generation in zero-shot setting. Science China Information Sciences 65 (4), 1-2.
(11)Qingbin Liu, Shizhu He, Cao Liu, Kang Liu, and Jun Zhao. Unsupervised Dialogue State Tracking for End-to-End Task-Oriented Dialogue with a Multi-Span Prediction Network[J]. Journal of Computer Science and Technology, 2022.
(12) Qingbin Liu, Shizhu He, Kang Liu, Shengping Liu, Jun Zhao. A Unified Shared-Private Network with Denoising for Dialogue State Tracking[J]. Journal of Computer Science and Technology, 2021, 36(6): 1407-1419.
(13) Qingbin Liu, Guirong Bai, Shizhu He, Cao Liu, Kang Liu, and Jun Zhao. Heterogeneous relational graph neural networks with adaptive objective for end-to-end task-oriented dialogue[J]. Knowledge-Based Systems, 2021, 227: 107186.
(14) Yinyu Lan, Shizhu He, Kang Liu, Xiangrong Zeng, Shengping Liu, Jun Zhao. Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion. BMC Medical Informatics Decis. Mak. 21-S(9): 335 (2021).
(15) Xiaoyan Yu, Qingbin Liu, Shizhu He, Kang Liu, Shengping Liu, Jun Zhao, Yongbin Zhou. Multi-strategy Knowledge Distillation Based Teacher-Student Framework for Machine Reading Comprehension. CCL 2021: 209-225.
(16) Qingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu, Jun Zhao. Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks. EMNLP (1) 2021: 2301-2311.
(17) Guirong Bai, Shizhu He, Kang Liu, Jun Zhao. Using Pre-trained Language Model to Enhance Active Learning for Sentence Matching[J]. Transactions on Asian and Low-Resource Language Information Processing, 2021, 21(2): 1-19.
(18) Fei Xia, Shizhu He, Kang Liu, Shengping Liu, Jun Zhao. Toward a Better Text Data Augmentation via Filtering and Transforming Augmented Instances. CCKS 2021.
(19) 徐遥, 何世柱, 刘康, 张弛, 焦飞, 赵军. 基于Beta分布和半监督学习的非确定性知识图谱嵌入模型, China Conference on Knowledge Graph and Semantic Computing(CCKS 2021).
(20)Guirong Bai, Shizhu He, Kang Liu, Jun Zhao, Zaiqing Nie. Pre-trained Language Model Based Active Learning for Sentence Matching. COLING 2020: 1495-1504.
(21) 宋挺; 郭展成; 何世柱; 刘康; 赵军; 刘升平.基于动态词遮掩的句子匹配预训练模型, China Conference on Knowledge Graph and Semantic Computing(CCKS 2020).
(22) 郭展成; 宋挺; 何世柱; 刘康; 赵军; 刘升平.基于动态知识选择的预训练模型, China Conference on Knowledge Graph and Semantic Computing(CCKS 2020).(获最佳论文提名奖)
(23) Shizhu He, Kang Liu, Weiting An. Learning to Align Question and Answer Utterances in Customer Service Conversation with Recurrent Pointer Networks. AAAI 2019: 134-141
(24) Cao Liu; Shizhu He; Kang Liu; Zaiqing Nie; Jun Zhao. Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019).
(25) Xiangrong Zeng; Shizhu He; Daojian Zeng; Kang Liu; Jun Zhao. Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019).
(26) Cao Liu; Shizhu He; Kang Liu; Jun Zhao. Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019).
(27)Xiang Zhang; Shizhu He; Kang Liu; Jun Zhao. AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019).
(28) Guirong Bai; Shizhu He; Kang Liu; Jun Zhao. Variational Attention for Commonsense Knowledge Aware Conversation Generation. The 8th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2019).
(29) Guirong Bai; Shizhu He; Kang Liu; Jun Zhao. Utterance Alignment in Custom Service by Integer Programming. The Eighteenth China National Conference on Computational Linguistics (CCL 2019),
(30) Cao Liu; Kang Liu; Shizhu He; Zaiqing Nie; Jun Zhao. Incorporating Interlocutor-Aware Context into Response Generation on Multi-Party Chatbots. The SIGNLL Conference on Computational Natural Language Learning (CoNLL 2019).
(31)Qingbin Liu; Shizhu He; Kang Liu; Jun Zhao, Shengping Liu. Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking (CCKS 2019). (获最佳论文奖)
科研活动
科研项目
指导学生
现指导学生
徐遥 硕士研究生 081104-模式识别与智能系统
王思懿 硕士研究生 081104-模式识别与智能系统
桂梁 硕士研究生 085400-电子信息
李想 硕士研究生 081104-模式识别与智能系统
王峙淇 硕士研究生 085400-电子信息
吴佳钰 硕士研究生 085400-电子信息