Complex Named Entity Recognition via Deep Multi-task Learning from Scratch

摘要：

　　Named Entity Recognition(NER)is the preliminary task in many basic NLP technologies and deep neural networks has shown their promising opportunities in NER task.However,the NER tasks covered in previous work are relatively simple,focusing on classic entity categories(Persons,Locations,Organizations)and failing to meet the requirements of newly-emerging application scenarios,where there exist more informal entity categories or even hierarchical category structures.In this paper,we propose a multi-task learning based subtask learning strategy to combat the complexity of modern NER tasks.We conduct experiments on a complex Chinese NER task,and the experimental results demonstrate the effectiveness of our approach.

关键词： Complex named entity recognition Multi-task learning Deep learning

作者: Guangyu Chen Tao Liu Deyuan Zhang Bo Yu Baoxun Wang

作者单位: School of Information,Renmin University of China,Beijing,China School of Computer,Shenyang Aerospace University,Shenyang,China Tricorn(Beijing)Technology Co.,Ltd,Beijing,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: 221-233

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）