事件关系检测是一项面向文本信息流进行事件关系判定的自然语言处理技术。事件关系检测的核心任务是以事件为基本语义单元,通过分析事件之间的语义关联特征,实现事件逻辑关系的识别与判定,包括关系识别(即识别有无逻辑关系)和关系判定(即判定逻辑关系类型,如“因果”关系)。目前,专门面向事件的逻辑关系分析与处理,尚未形成一套完整的研究体系。针对这一问题,该文借助篇章分析、事件抽取和场景理解等相关领域中的概念与数据资源,尝试建立一套事件关系检测的任务和研究体系,包括任务定义、关系体系划分、语料采集与标注、评价方法等。同时,该文着重分析和对比了事件关系检测与篇章关系检测的差异,并给出了事件关系检测任务的难点与挑战。
Abstract
Event relation detection is the task to detect the event relation from information stream of texts. Treating the event as the basic semantic unit, the relation type is determined by analyzing the feature of semantic relevancy between events. The event relation detection includes event relation identification (identifying whether the event pair is related or not) and event relation type decision (deciding which relation between relevance events, e.g. cause relation). In this paper, we try to establish a system of event relation detection in light of the concepts and data resources of discourse analysis, event extraction and scene understanding, covering the issues of the task definition, classification system of event types, corpora acquisition and annotations evaluation methodology, etc. Finally, we not only emphasize the analysis and comparison of the difference between event relation detection and discourse relation analysis, but also present the difficulty and challenge of the event relation detection.
关键词
事件关系检测 /
篇章分析 /
事件 /
论元 /
语义关系
{{custom_keyword}} /
Key words
event relation detection /
discourse relation analysis /
event /
argument /
semantic relation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1]T Chklovski, P Pantel. Global path-based refinement of noisy graphs applied to verb semantics[C]//Proceedings of Joint Conference on Natural Language Processing, Jeju Island, Korea, 2005: 792-803.
[2] P Pantel, M Pennacchiotti. Espresso: leveraging generic patterns for automatically harvesting semantic relations[C]//Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL, Sydney, Australia, 2006: 113-120.
[3] Z S Harris. Mathematical Structure of Language[M]. New York, 1968.
[4] D Lin, P Pantel. Discovery of Inference Rules from Text[C]//Proceeding of the 7th ACM SIGKDD, San Francisco, California, USA, 2001: 323-328.
[5] E Pitler, M Raghupathy, H Mehta, et al. Easily identifiable discourse relations[C]//Proceedings of the 22nd International Conference on the COLING, 2008: 87-90.
[6] P E, R M, N HM, et al. Easily identifiable discourse relations[C]//Proceedings of the 22nd International Conference on Computational Linguistics (COLING 2008), Posters, Manchester, UK, 2008: 87-90.
[7] The Penn Discourse Treebank 2.0 Annotation Manual[R], 2007.
[8] Y Hong, X P Zhou, T T Che,et al. Cross-Argument Inference for Implicit Discourse Relation recognition[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management(CIKM 2012),2012: 295-304.
[9] N Daniel, D Radev, T Allison. Sub-event based multi-document summarization[C]//Proceedings of the Association for Computational Linguistics Morristown, NJ, USA, 2003: 9-16.
[10] H Yang, T S Chua, S G Wang, et al. Structured use of external knowledge for event-based open domain question answering[C]//Proceedings of the 26th Int’l ACM SIGIR Conference, Toronto, Canada, 2003: 33-40.
[11] S A Mirroshandel, G G Sani. Temporal Relations Learning with a Bootstrapped Cross-document Classifier[C]//Proceedings of the 4th International Workshop on Semantic Evaluations, Prague, 2007: 75-80.
[12] Y Hong, J F Zhang, B Ma, et al. Using Cross-Entity Inference to Improve Event Extraction [C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, Portland, Oregon, June, 2011: 19-24.
[13] C J Fillmore.Frame semantics and the nature of language[J].Annals of the New York Academy of Sciences,1976: 20-32.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61003152,61272259,61272260)
{{custom_fund}}
PDF(849 KB)
