DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization

We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization. Given any document-summary pair, we estimate a salience score, which is modeled using an attention-based deep neural network, to represent the salience degree of the summary for yielding the document. We devise a contrastive training strategy to learn the salience estimation network, and then use the learned salience score as a guide and iteratively extract the most salient sentences from the document as our generated summary. In experiments, our model not only achieves state-of-the-art ROUGE scores on CNN/Daily Mail dataset, but also shows strong robustness in the out-of-domain test on DUC2007 test set. Moreover, our model reaches a ROUGE-1 F-1 score of 39. 41 on CNN/Daily Mail test set with merely 1/100 training set, demonstrating a tremendous data efficiency.

Authors

• Jiaxin Shi Cloud BU, Huawei Technologies
• Chen Liang Shenzhen Geim Graphene Center, Institute of Materials Research, Tsinghua Shenzhen International Graduate School, Tsinghua University
• Lei Hou Department of Computer Science and Technology, Tsinghua University
• Juanzi Li Department of Computer Science and Technology, Tsinghua University
• Zhiyuan Liu Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications, Chongqing, China Key Laboratory of Cyberspace Big Data Intelligent Security, Ministry of Education
• Hanwang Zhang Nanyang Technological University

Keywords

No keywords are indexed for this paper.