• 数据挖掘 •

### 带有覆盖率机制的文本摘要模型研究

1. 1. 数据工程与知识工程教育部重点实验室（中国人民大学 信息学院），北京 100872
2. 清华大学 经济管理学院，北京 100084
• 出版日期:2019-02-01 发布日期:2019-01-25

### Research on Text Summarization Model with Coverage Mechanism

GONG Yifan1, LIU Hongyan2, HE Jun1+, YUE Yongjiao1, DU Xiaoyong1

1. 1. Key Laboratory of Data Engineering and Knowledge Engineering (School of Information, Renmin University of China), Ministry of Education, Beijing 100872, China
2. School of Economics and Management, Tsinghua University, Beijing 100084, China
• Online:2019-02-01 Published:2019-01-25

Abstract: In recent years, text information has experienced explosive growth, and people haven??t enough time to read all these texts. Therefore, how to automatically extract key information from massive texts is particularly important. Text summarization technology can solve this problem. At present, sequence to sequence model with attention mechanism is usually used to generate text summary. However, the attention mechanism is independent at  each moment, and the text information generated at the previous moment is not taken into account. This results in the term repetition in the summary. In order to solve this problem, this paper proposes new coverage models. In these models, coverage vector is developed to record the historical attention weight distribution and adjust the current attention weight distribution, making the summarization model pay more attention to information that is not used. The experiment conducted on the Sina Weibo data set shows that the proposed model with coverage mechanism performs better than the normal sequence to sequence model.