Improving Event Detection via Information Sharing among Related Event Types

摘要：

　　Event detection suffers from data sparseness and label imbalance prob-lem due to the expensive cost of manual annotations of events.To address this problem,we propose a novel approach that allows for information sharing among related event types.Specifically,we employ a fully connected three-layer artifi-cial neural network as our basic model and propose a type-group regularization term to achieve the goal of information sharing.We conduct experiments with different configurations of type groups,and the experimental results show that in-formation sharing among related event types remarkably improves the detecting performance.Compared with state-of-the-art methods,our proposed approach achieves a better F1 score on the widely used ACE 2005 event evaluation dataset.

作者: Shulin Liu Yubo Chen Kang Liu Jun Zhao Zhunchen Luo Wei Luo

作者单位: National Laboratory of Pattern RecognitionInstitute of Automation,Chinese Academy of Sciences,Beijin National Laboratory of Pattern RecognitionInstitute of Automation,Chinese Academy of Sciences,Beijin China Defense Science and Technology Information Center,Beijing,100142,China

会议类型: 国内会议

会议名称: 第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

会议地点: 南京

会议语种:英文

页码: 1-12

在线出版日期: 2017-10-13（万方平台首次上网日期，不代表论文的发表时间）