Journal of Frontiers of Computer Science and Technology ›› 2018, Vol. 12 ›› Issue (3): 423-431.DOI: 10.3778/j.issn.1673-9418.1611074

Previous Articles     Next Articles

Combining Context Dependency and Sentence Semantic Representation for Event Nugget Detection

WANG Kai, HONG Yu+, QIU Yingying, YAO Jianmin, ZHOU Guodong   

  1. School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China
  • Online:2018-03-01 Published:2018-03-08

融合上下文依赖和句子语义的事件线索检测研究

王  凯,洪  宇+,邱盈盈姚建民周国栋   

  1. 苏州大学 计算机科学与技术学院,江苏 苏州 215006

Abstract: Event nugget detection aims to extract words or phrases which trigger events from the free text automatically. Existing methods about English event nugget detection rely on feature extraction tools, which will cause error propagation. Besides, they ignore the dependency between the candidate word and the context and the semantic     information of the sentence, which are helpful to detect event nugget. This paper proposes a neural network method, which uses bidirectional long short-term memory neural network (Bi-LSTM) to crawl the dependency of sentence context while using the gated recurrent neural network (GRNN) to learn sentence semantic representation. Then this paper combines these information to improve the ability of identifying event nugget. The experimental results on the corpus of KBP 2015 evaluation show that the proposed method is effective and significantly higher than baseline methods.

Key words: event nugget detection, neural network, long short-term memory (LSTM)

摘要: 事件线索检测旨在从自由文本中自动抽取触发事件的词或短语。现有的英文事件线索检测方法依赖于特征提取工具,这样会造成错误传递,而且忽略了待测词与上下文的依赖关系和句子的语义信息,这些信息对事件线索检测是很有帮助的。提出一种神经网络方法,利用双向长短时记忆网络(bidirectional long short- term memory,Bi-LSTM)抓取待测词在句子中的上下文依赖,同时使用门控循环神经网络(gated recurrent neural network,GRNN)学习句子的语义表示,融合这两种信息来提高事件线索词的识别能力。在KBP 2015评测语料上的实验结果显示,该方法是有效的,并且性能比baseline方法有显著提高。

关键词: 事件线索检测, 神经网络, 长短时记忆网络(LSTM)