计算机科学 ›› 2018, Vol. 45 ›› Issue (6): 204-207.doi: 10.11896/j.issn.1002-137X.2018.06.036

• 人工智能 • 上一篇    下一篇

事件因果与时序关系识别的联合推理模型

黄一龙, 李培峰, 朱巧明   

  1. 苏州大学计算机科学与技术学院 江苏 苏州215006;
    江苏省计算机信息处理技术重点实验室 江苏 苏州215006
  • 收稿日期:2017-03-18 出版日期:2018-06-15 发布日期:2018-07-24
  • 作者简介:黄一龙(1991-),男,硕士生,主要研究领域为中文信息处理;李培峰(1971-),男,教授,硕士生导师,主要研究领域为中文信息处理,E-mail:pfli@suda.edu.cn(通信作者);朱巧明(1963-),男,教授,博士生导师,主要研究领域为中文信息处理
  • 基金资助:
    本文受国家自然科学基金(61472265),国家自然科学基金重点项目(61331011),江苏省前瞻性联合研究项目(BY2014059-08)资助

Joint Model of Events’ Causal and Temporal Relations Identification

HUANG Yi-long, LI Pei-feng, ZHU Qiao-ming   

  1. School of Computer Science and Technology,Soochow University,Suzhou,Jiangsu 215006,China;
    Province Key Lab of Computer Information Processing Technology of Jiangsu,Suzhou,Jiangsu 215006,China
  • Received:2017-03-18 Online:2018-06-15 Published:2018-07-24

摘要: 事件的因果关系与时序关系是两种重要的事件关系。已有研究往往将事件的因果关系与时序关系识别分别看成两项独立的任务,这种做法忽略了两种事件关系之间的关联性。文中提出使用整数线性规划方法来构建基于事件因果关系与时序关系识别的联合推理模型。联合模型对两种事件关系进行约束,在分类器模型的基础上对结果进行优化。最终结果表明,所提联合推理模型能够有效增强识别性能。

关键词: 联合模型, 时序关系, 事件, 因果关系

Abstract: Causal and temporal relations of events are both important event relationships.The previous work regarded theidentification of causal and temporal relations of events as two independent tasks,ignoring the association between them.This paper applied integer linear programming(ILP) to construct joint model of event based onidentification of causal and temporal of event.Based on classifier model,the joint model optimizes the recognition results through constraints.The experimental results show that this joint model significantly enhances the identification performance.

Key words: Causal relation, Event, Joint model, Temporal relation

中图分类号: 

  • TP391
[1]WOLFF P.Representing causation[J].Journal of Experimental Psychology:General,2007,136(1):82-111.
[2]KHOO C S G,CHAN S,NIU Y.Extracting Causal Knowledge from a Medical Database Using Graphical Patterns[C]//Mee-ting of the Association for Computational Linguistics.2002:336-343.
[3]GIRJU R,DAN M.Mining Answers for Causation Questions[C]//AAAI Symposium on Mining Answers from texts and Knowledge Bases.2002.
[4]BETHARD S,CORVEY W,KLINGENSTEIN S,et al.Building a Corpus of Temporal-Causal Structure[C]//International Conference on Language Resources and Evaluation,Marrakech,Morocco.DBLP,2008:908-915.
[5]BETHARD S,MARTIN J H.Learning semantic links from a corpus of parallel temporal and causal relations[C]//Meeting of the Association for Computational Linguistics on Human Language Technologies:Short Papers.Association for ComputationalLinguistics,2008:177-180.
[6]DO Q X,CHAN Y S,ROTH D.Minimally supervised event causality identification[C]//Conference on Empirical Methods in Natural Language Processing.Association for Computational Linguistics,2011:294-303.
[7]RADINSKY K,DAVIDOVICH S,MARKOVITCH S.Learning causality for news events prediction[C]//International Confe-rence on World Wide Web.ACM,2012:909-918.
[8]RIAZ M,GIRJU R.Recognizing Causality in Verb-Noun Pairs via Noun and Verb Semantics[C]//Eacl 2014 Workshop on Computational Approaches to Causality in Language.2014:48-57.
[9]MIRZA P,SPRUGNOLI R,TONELLI S,et al.Annotating causality in the TempEval-3 corpus[C]//Proceedings of the EACL 2014 Workshop on Computational Approaches to Causality in Language (CAtoCL).2014:10-19.
[10]MIRZA P.Extracting Temporal and Causal Relations between Events[C]//Proceedings of the ACL 2014 Student Research Workshop.Baltimore,Maryland USA,2014:10-17.
[11]MIRZA P,TONELLI S.CATENA:CAusal and TEmporal relation extraction from NAtural language texts[C]//The 26th International Conference on Computational Linguistics.2016:64-75.
[12]MANI I,VERHAGEN M,WELLNER B,et al.Machine learning of temporal relations[C]//Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2006:753-760.
[13]CHAMBERS N,WANG S,JURAFSKY D.Classifying temporal relations between events[C]//Meeting of the ACL on Interactive Poster and Demonstration Sessions.Association for Computational Linguistics,2007:173-176.
[14]CHAMBERS N,DAN J.Jointly Combining Implicit Constraints Improves Temporal Ordering[C]//Conference on Empirical Methods in Natural Language Processing.2009:698-706.
[15]ZHENG X,LI P F,ZHU Q M.Global Inference for Temporal Relations Between Chinese Events[J].Journal of Chinese Information Processing,2016,30(5):129-135.(in Chinese)
郑新,李培峰,朱巧明.基于全局优化的中文事件时序关系推理方法[J].中文信息学报,2016,30(5):129-135.
[16]HUANG Y L,LI P F,ZHU Q M.The Construction of Chinese Relevant Event Corpus and Its Recognition Approach[J] .Computer Engineering and Science,2015,37(12):2306-2311.(in Chinese)
黄一龙,李培峰,朱巧明.中文事件相关性语料库构建及识别方法[J].计算机工程与科学,2015,37(12):2306-2311.
[17]ZHENG X,LI P F,ZHU Q M.Annotation and Classification of Temporal Relation Between Chinese Events[J].ComputerScien-ce,2015,42(7):276-279.(in Chinese)
郑新,李培峰,朱巧明,等.中文事件时序关系的标注和分类方法[J].计算机科学,2015,42(7):276-279.
[1] 周旭, 钱胜胜, 李章明, 方全, 徐常胜.
基于对偶变分多模态注意力网络的不完备社会事件分类方法
Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification
计算机科学, 2022, 49(9): 132-138. https://doi.org/10.11896/jsjkx.220600022
[2] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[3] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[4] 徐化池, 史殿习, 崔玉宁, 景罗希, 刘聪.
面向事件相机的时间信息融合网络框架
Time Information Integration Network for Event Cameras
计算机科学, 2022, 49(5): 43-49. https://doi.org/10.11896/jsjkx.210400047
[5] 缪峰, 王萍, 李太勇.
基于事件动作方向的隐式因果关系抽取方法
Implicit Causality Extraction Method Based on Event Action Direction
计算机科学, 2022, 49(3): 276-280. https://doi.org/10.11896/jsjkx.211100249
[6] 李素, 宋宝燕, 李冬, 王俊陆.
面向金融活动的复合区块链关联事件溯源方法
Composite Blockchain Associated Event Tracing Method for Financial Activities
计算机科学, 2022, 49(3): 346-353. https://doi.org/10.11896/jsjkx.210700068
[7] 乔杰, 蔡瑞初, 郝志峰.
一种基于信息瓶颈的因果关系挖掘方法
Mining Causality via Information Bottleneck
计算机科学, 2022, 49(2): 198-203. https://doi.org/10.11896/jsjkx.210100053
[8] 侯春萍, 赵春月, 王致芃.
基于自反馈最优子类挖掘的视频异常检测算法
Video Abnormal Event Detection Algorithm Based on Self-feedback Optimal Subclass Mining
计算机科学, 2021, 48(7): 199-205. https://doi.org/10.11896/jsjkx.200800146
[9] 卿来云, 张建功, 苗军.
在线异常事件检测的时序建模
Temporal Modeling for Online Anomaly Detection
计算机科学, 2021, 48(7): 206-212. https://doi.org/10.11896/jsjkx.200900093
[10] 程思伟, 葛唯益, 王羽, 徐建.
BGCN:基于BERT和图卷积网络的触发词检测
BGCN:Trigger Detection Based on BERT and Graph Convolution Network
计算机科学, 2021, 48(7): 292-298. https://doi.org/10.11896/jsjkx.200500133
[11] 程铁军, 王曼.
基于变权组合的突发事件网络舆情趋势预测
Network Public Opinion Trend Prediction of Emergencies Based on Variable Weight Combination
计算机科学, 2021, 48(6A): 190-195. https://doi.org/10.11896/jsjkx.200600094
[12] 张姝楠, 曹峰, 郭倩, 钱宇华.
一种基于时序关系网络的逻辑推理方法
Logical Reasoning Method Based on Temporal Relation Network
计算机科学, 2021, 48(5): 239-246. https://doi.org/10.11896/jsjkx.201000171
[13] 丁玲, 向阳.
基于分层次多粒度语义融合的中文事件检测
Chinese Event Detection with Hierarchical and Multi-granularity Semantic Fusion
计算机科学, 2021, 48(5): 202-208. https://doi.org/10.11896/jsjkx.200800038
[14] 吴凡, 朱培培, 王中卿, 李培峰, 朱巧明.
基于字词联合表示的中文事件检测方法
Chinese Event Detection with Joint Representation of Characters and Words
计算机科学, 2021, 48(4): 249-253. https://doi.org/10.11896/jsjkx.200300156
[15] 钱胜胜, 张天柱, 徐常胜.
多媒体社会事件分析综述
Survey of Multimedia Social Events Analysis
计算机科学, 2021, 48(3): 97-112. https://doi.org/10.11896/jsjkx.210200023
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!