计算机科学 ›› 2022, Vol. 49 ›› Issue (3): 276-280.doi: 10.11896/jsjkx.211100249
缪峰1, 王萍2, 李太勇2
MIU Feng1, WANG Ping2, LI Tai-yong2
摘要: 抽取事件之间的因果关系能够应用于自动问答、知识提取、常识推理等方面。隐式因果关系由于缺乏明显的词汇特征和中文复杂的句法结构,使得其抽取极为困难,已成为当前研究的难点。相比而言,显示因果关系的抽取比较容易、准确率高,且因果关系事件之间的逻辑关系稳定。为此,文中提出了一种原创的方法,首先通过对抽取的显示因果事件对进行事件动作的归一化处理后形成事件方向,然后对事件主体进行泛化处理,最终形成标准的匹配因果事件对集合。利用此集合根据事件相似度从语句中抽取隐式因果事件对。为了识别更多的隐式因果关系,文中同时提出了一种因果连接词发现算法。在网易财经、腾讯财经和新浪财经上爬取的实验数据验证,对事件动作进行归一化处理后形成事件方向相比传统方法抽取准确率提高了1.02%。
中图分类号:
[1]OH J H,TORISAWA K,HASHIMOTO C,et al.Why-Question Answering Using Intra-and Inter-Sentential Causal Relations[C]//Proceedings of the 51st ACL.Sofia,Bulgaria:Association for Computational Linguistics,2013:1733-1743. [2]HASHIMOTO C,TORISAWA K,KLOETZER J,et al.Towardfuture scenario generation:Extracting event causality exploiting semantic relation,context,and association features[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers).2014:987-997. [3]YANG P F.Research and Construction of causal knowledgebase[D].Changchun:Jilin University,2016. [4]DOAN S,YANG E W,TILAK S S,et al.Extracting health-related causality from twitter messages using natural language processing[J].BMC Medical Informatics and Decision Making,2019,19(3):71-77. [5]AN N,XIAO Y,YUAN J,et al.Extracting causal relations from the literature with word vector mapping[J].Computers in Biology and Medicine,2019,115:103524. [6]CUI Y,LIU C H.Research on Causal Association Rule Mining Based on Constraint Network[J].Computer Science,2016,43(11A):466-468. [7]DRURY B,ROCHA C,MOURA M F,et al.The Extractionfrom News Stories a Causal Topic Centred Bayesian Graph for Sugarcane[C]//Proceedings of the 20th International Database Engineering & Applications Symposium.2016:364-369. [8]LEE D,SHIN H.Disease causality extraction based on lexical semantics and document-clause frequency frombiomedical literature[J].BMC Medical Informatics and Decision Making,2017,17(1):1-9. [9]IZUMI K,SAKAJI H.Economic causal-chain search using text mining technology[C]//Proceedings of the First Workshop on Financial Technology and Natural Language Processing.2019:61-65. [10]MIRZA P,TONELLI S.Catena:Causal and temporal relation extraction from natural language texts[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.2016:64-75. [11]YANG J C,CAO Y,HU Q,et al.Relation Classification of Chinese Causal Compound Sentences Based on Transformer Model and Relational Word Feature[J].Computer Science,2021,48(6A):295-298. [12]YU F,MOH M,MOH T S.Towards extracting drug-effect relation from Twitter:a supervised learning approach[C]//2016 IEEE 2nd International Conference on Big Data Security on Cloud (BigDataSecurity),IEEE International Conference on High Performance and Smart Computing (HPSC),and IEEE International Conference on Intelligent Data and Security (IDS).IEEE,2016:339-344. [13]DING W,ZHOU F,MIAO J P,et al.Temporal Relation Recognition Method for News Events Based on Cross Event Theory[J].Computer Engineering,2017,6:189-194. [14]KRUENGKRAI C,TORISAWA K,HASHIMOTO C,et al.Improving event causality recognition with multiple background knowledge sources using multi-column convolutional neural networks[C]//Thirty-First AAAI Conference on Artificial Intelligence.2017. [15]HUANG Y L,LI P F,ZHU Q M.Joint Model of Events’ Cau-sal and Temporal Relations Identification[J].Computer Science,2018,45(6):204-207. [16]TIAN S W,ZHOU X F,YU L,et al.Causal Relation Extraction of Uyghur Events Based on Bidirectional Long Short-term Me-mory Model[J].Journal of Electronics and Information Technology,2018,40(1):200-208. [17]KILICOGLU H.Inferring implicit causal relationships in bio-medical literature[C]//Proceedings of the 15th Workshop on Biomedical Natural Language Processing.2016:46-55. [18]AYYANAR R,KOOMULLIL G,RAMASANGU H.CausalRelation Classification using Convolutional Neural Networks and Grammar Tags[C]//2019 IEEE 16th India Council International Conference (INDICON).IEEE,2019:1-3. [19]HASHIMOTO C.Weakly Supervised Multilingual CausalityExtraction from Wikipedia[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).2019:2979-2990. [20]ZHONG J,YU L,TIAN S W,et al.Causal Relation Extraction of Uyghur Emergency Events Based on Cascaded Model[J].Acta Automatica Sinica,2014,40(4):771-779. [21]MA J H,HAO Y J,ZHANG Y M.Causal Relation Label Based on Cascading Skip-chain Conditional Random Fields[J].Journal of Zhengzhou University(Natural Science Edition),2016,48(4):54-59. [22]ZHOU W.The Construction and Application of KnowledgeGraph Incorporating Causal Events[D].Shanghai:East China Normal University,2019. [23]XU J H,ZUO W L,LIANG S L,et al.Causal Relation Extraction Based on Graph Attention Networks[J].Journal of Computer Research and Development,2020,57(1):159-174. [24]MU W J.Judgment of News Oriented Argument Causation[D].Harbin:Harbin Institute of Technology,2018. |
[1] | 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 |
[2] | 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 |
[3] | 叶松涛, 周扬正, 范红杰, 陈正雷. 融合因果关系和时空图卷积网络的人体动作识别 Joint Learning of Causality and Spatio-Temporal Graph Convolutional Network for Skeleton- based Action Recognition 计算机科学, 2021, 48(11A): 130-135. https://doi.org/10.11896/jsjkx.201200205 |
[4] | 余杰, 纪斌, 刘磊, 李莎莎, 马俊, 刘慧君. 面向中文医疗事件的联合抽取方法 Joint Extraction Method for Chinese Medical Events 计算机科学, 2021, 48(11): 287-293. https://doi.org/10.11896/jsjkx.201200016 |
[5] | 朱培培, 王中卿, 李寿山, 王红玲. 基于篇章信息和Bi-GRU的中文事件检测 Chinese Event Detection Based on Document Information and Bi-GRU 计算机科学, 2020, 47(12): 233-238. https://doi.org/10.11896/jsjkx.191100031 |
[6] | 高李政, 周刚, 黄永忠, 罗军勇, 王树伟. 基于Zipf's共生矩阵分解的开放域事件向量计算方法 Open Domain Event Vector Algorithm Based on Zipf's Co-occurrence Matrix Factorization 计算机科学, 2020, 47(10): 207-214. https://doi.org/10.11896/jsjkx.191200183 |
[7] | 高李政, 周刚, 罗军勇, 兰明敬. 元事件抽取研究综述 Survey on Meta-event Extraction 计算机科学, 2019, 46(8): 9-15. https://doi.org/10.11896/j.issn.1002-137X.2019.08.002 |
[8] | 姚宁, 苗夺谦, 张志飞. 因果信息在不同粒度上的迁移性 Transportability of Causal Information Across Different Granularities 计算机科学, 2019, 46(2): 178-186. https://doi.org/10.11896/j.issn.1002-137X.2019.02.028 |
[9] | 黄一龙, 李培峰, 朱巧明. 事件因果与时序关系识别的联合推理模型 Joint Model of Events’ Causal and Temporal Relations Identification 计算机科学, 2018, 45(6): 204-207. https://doi.org/10.11896/j.issn.1002-137X.2018.06.036 |
[10] | 崔阳,刘长红. 基于约束网络的因果关联规则挖掘研究 Research on Causal Association Rule Mining Based on Constraint Network 计算机科学, 2016, 43(Z11): 466-468. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.104 |
[11] | 张德平,刘国强,张柯. 基于GMDH因果关系的软件缺陷预测模型 Software Defect Prediction Model Based on GMDH Causal Relationship 计算机科学, 2016, 43(7): 171-176. https://doi.org/10.11896/j.issn.1002-137X.2016.07.031 |
[12] | 徐霞,李培峰,朱巧明. 半监督中文事件抽取中的模板过滤和转换方法 Pattern Filtering and Conversion Methods for Semi-supervised Chinese Event Extraction 计算机科学, 2015, 42(2): 253-255. https://doi.org/10.11896/j.issn.1002-137X.2015.02.052 |
[13] | 郭喜跃,何婷婷. 信息抽取研究综述 Survey about Research on Information Extraction 计算机科学, 2015, 42(2): 14-17. https://doi.org/10.11896/j.issn.1002-137X.2015.02.003 |
[14] | 郑影,李大辉. 面向微博内容的信息抽取模型研究 Research on Information Extration Model for Microblog Content 计算机科学, 2014, 41(2): 270-275. |
[15] | 刘炜,徐文杰,唐英英,付剑锋,张旭洁,刘宗田. 基于扩展描述逻辑和逻辑程序的事件动作形式化表示与推理 Formalized Representation and Reasoning of Event Action Based on Extended Description Logic and Logic Program 计算机科学, 2014, 41(1): 116-125. |
|