Recognizing Macro Chinese Discourse Structure on Label Degeneracy Combination Model

摘要：

　　Discourse structure analysis is an important task in Natural Language Processing(NLP)and it is helpful to many NLP tasks,such as automatic summarization and information extraction.However,there are only a few researches on Chinese macro discourse structure analysis due to the lack of annotated corpora.In this paper,combining structure recognition with nuclearity recognition,we propose a Label Degeneracy Combination Model(LD-CM)to find the solution of structure recognition in the solution space of nuclearity recognition.Experimental results on the Macro Chinese Discourse TreeBank(MCDTB)show that our model improves the accuracy by 1.21%,compared with the baseline system.

关键词： Label degeneracy Combination model Macro discourse structure

作者: Feng Jiang Peifeng Li Xiaomin Chu Qiaoming Zhu Guodong Zhou

作者单位: School of Computer Science and Technology,Soochow University,Suzhou,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: 92-104

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）