Event Detection via Recurrent Neural Network and Argument Prediction

摘要：

　　This paper tackles the task of event detection,which involves identifying and categorizing the events.Currently event detection remains a challenging task due to the difficulty at encoding the event semantics in complicate contexts.The core semantics of an event may derive from its trigger and arguments.However,most of previous studies failed to capture the argument semantics in event detection.To address this issue,this paper first provides a rule-based method to predict candidate arguments on the event types of possibilities,and then proposes a recurrent neural network model RNN-ARG with the attention mechanism for event detection to capture meaningful semantic regularities form these predicted candidate arguments.The experimental results on the ACE 2005 English corpus show that our approach achieves competitive results compared with previous work.

关键词： Event detection Argument prediction Recurrent neural network

作者: Wentao Wu Xiaoxu Zhu Jiaming Tao Peifeng Li

作者单位: School of Computer Science and Technology,Soochow University,Suzhou,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 235-245

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）