An End-to-End Scalable Iterative Sequence Tagging with Multi-Task Learning

摘要：

　　Multi-task learning(MTL)models,which pool examples arisen out of several tasks,have achieved remarkable results in language processing.However,multi-task learning is not always effective when compared with the single-task methods in sequence tagging.One possible reason is that existing methods to multi-task sequence tagging often reply on lower layer parameter sharing to connect different tasks.The lack of interactions between different tasks results in limited performance improvement.In this paper,we propose a novel multi-task learning architecture which could iteratively utilize the prediction results of each task explicitly.We train our model for part-of-speech(POS)tagging,chunking and named entity recognition(NER)tasks simultaneously.Experimental results show that without any task-specific features,our model obtains the state-of-the-art performance on both chunking and NER.

关键词： Multi-task learning Interactions Sequence tagging

作者: Lin Gui Jiachen Du Zhishan Zhao Yulan He Ruifeng Xu Chuang Fan

作者单位: Harbin Institute of Technology(Shenzhen),Shenzhen,China;Aston University,Birmingham,UK Harbin Institute of Technology(Shenzhen),Shenzhen,China Baidu Inc.,Beijing,China Aston University,Birmingham,UK

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: 288-298

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）