事件关系识别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。事件关系识别的核心任务是以事件为基本语义单元,通过分析事件的篇章结构信息及语义特征,实现事件逻辑关系的浅层检测(即判定任意事件之间是否存在逻辑相关性)。该文通过利用同一话题下事件的核心词及实体的分布特性,针对同一话题下事件关系识别任务,提出一种基于核心词和实体推理的事件关系识别方法。实验结果显示,该文方法明显优于基于事件语义依存线索的事件关系识别方法,F值获得了15.34%的提升。
Abstract
Event relation recognition, as one of natural language processing technologies, faces information stream of texts detecting event relation. The key to event relation recognition is to detect latent logical relation (deciding whether events hold logical relation or not) between events by analyzing the corresponding discourse structure and semantic features of events, with the techniques of semantic relation recognition and inference. This paper proposes an event relation recognition method based on the inference of the event term and entityunder the same topic.Compared with the method based on dependency cue inference, theproposed method achieves 15.34% improvement.
关键词
实体分布 /
核心词分布 /
虚拟相关事件 /
事件关系
{{custom_keyword}} /
Key words
entity distribution /
event term distribution /
virtual dependency event /
event relation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] W J Li, W Xu, M L Wu, et al. Extractive summarization using inter- and intra- event relevance[C]//Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, 2006: 369-376.
[2] T Chklovski, P Pantel. Global path-based refinement of noisy graphs applied to verb semantics[C]//Proceedings of the Joint Conference on Natural Language Processing, Jeju Island, Korea, 2005: 792-803.
[3] 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.
[4] Z S Harris. Mathematical Structure of Language[M]. New York, 1968.
[5] D Lin, P Pantel. Discovery of Inference Rules from Text[C]//Proceedings of the 7th ACM SIGKDD, San Francisco, California, USA, 2001: 323-328.
[6] I Szpektor, H Tanev, I Dagan, et al. Scaling Web-based Acquisition of Entailment Relations[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, Barcelona, Spain, 2004: 41-48.
[7] 马彬, 洪宇, 杨雪蓉, 姚建民, 朱巧明.基于语义依存线索的事件关系识别方法研究[J].北京大学学报, 2012, 6:109-116.
[8] 洪宇, 张宇, 刘挺, 李生.话题检测与跟踪的评测及研究综述. 中文信息学报[J], 2007, 6: 71-84.
[9] Y Hong, J F Zhang, B Ma, et al. Using Cross-Entity Inference to Improve Event Extraction[C]//Proceedings ACL 2011: 1127-1136.
[10] B J Frey, D Duerk. Clustering by Passing Messages Between Data Points[J]. Science. 2007, 315: 972-976.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61003152,61272259,60970056),江苏省高校自然科学基金重大项目(11KIJ520003),苏州市自然科学基金(No. SYG201030, SH201212
{{custom_fund}}
PDF(4067 KB)
