Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition

摘要：

　　State-of-the-art systems of Chinese Named Entity Recognition(CNER)require large amounts of hand-crafted features and domain-specific knowledge to achieve high performance.In this paper,we apply a bidirectional LSTM-CRF neural network that utilizes both character-level and radical-level representations.We are the first to use character-based BLSTM-CRF neural architecture for CNER.By contrasting the results of different variants of LSTM blocks,we find the most suitable LSTM block for CNER.We are also the first to investigate Chinese radical-level representations in BLSTM-CRF architecture and get better performance without carefully designed features.We evaluate our system on the third SIGHAN Bakeoff MSRA data set for simplfied CNER task and achieve state-of-the-art performance 90.95%F1.

关键词： BLSTM-CRF radical features Named Entity Recognition

作者: Chuanhai Dong Jiajun Zhang Chengqing Zong Hattori Masanori Di Hui

作者单位: National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beiji Toshiba(China)R&D Center

会议类型: 国际会议

会议名称: 第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)

会议地点: 昆明

会议语种:英文

页码: 1-12

在线出版日期: 2016-12-02（万方平台首次上网日期，不代表论文的发表时间）