Recurrent Neural Word Segmentation with Tag Inference

摘要：

　　In this paper,we present a Long Short-Term Memory(LSTM)based model for the task of Chinese Weibo word segmentation.The model adopts a LSTM layer to capture long-range dependencies in sen-tence and learn the underlying patterns.In order to infer the optimal tag path,we introduce a transition score matrix for jumping between tags of successive characters.Integrated with some unsupervised features,the performance of the model is further improved.Finally,our model achieves a weighted F1-score of 0.8044 on close track,0.8298 on the semi-open track.

关键词： Chinese Word Segmentation LSTM Weibo

作者: Qianrong Zhou Long Ma Zhenyu Zheng Yue Wang Xiaojie Wang

作者单位: School of Computer,Beijing University of Posts and Telecommunications,Beijing,China

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: 1-11

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）