UIDS:A Multilingual Document Summarization Framework Based on Summary Diversity and Hierarchical Topics

摘要：

　　In this paper,we put forward UIDS,a new high-performing extensible framework for extractive MultiLingual Document Summariza-tion.Our approach looks on a document in a multilingual corpus as an item sequence set,in which each sentence is an item sequence and each item is the minimal semantic unit.Then we formalize the extractive summary as summary diversity sampling problem that considers topic diversity and redundancy at the same time.The topic diversity is re-flected using hierarchical topic models,the redundancy is reflected using similarity and the summary diversity is enhanced using Determinan-tal Point Processes.We then illustrate how this method encompasses a framework that is amenable to compute summaries for MultiLingual Single-and Multi-documents.Experiments on the MultiLing summariza-tion task datasets demonstrate the effectiveness of our approach.

关键词： Multilingual Document Summarization Summary Diver-sity Determinantal Point Processes

作者: Lei Li Yazhao Zhang Junqi Chi Zuying Huang

作者单位: Center for Intelligence Science and Technology,School of Computer Beijing University of Posts and Telecommunications,Beijing,P.R.China

会议类型: 国内会议

会议名称: 第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

会议地点: 南京

会议语种:英文

页码: 1-12

在线出版日期: 2017-10-13（万方平台首次上网日期，不代表论文的发表时间）