DCDSum: An interpretable extractive summarization framework based on contrastive learning method

As the phenomenon of knowledge overload becomes more and more obvious, the automatic summarization technology still needs to break through the bottleneck in order to improve the application value and expand the scope of the application. Traditional training paradigms for extractive summarization systems suffer from the inconsistency in training and evaluation. In this paper, we propose an innovative and interpretable contrastive learning based framework for extractive summarization called DCDSum, which comprises a Diverse Oracle evaluator, a Contrastive learning extractor, and a Dynamic Top-k selector. Different from previous models that consider the extractive summarization task as a sequence labeling problem, our contrastive learning extractor treats it as a sentence reranking problem and introduces contrastive loss to achieve it, which can bridge the gap between objective function and evaluation metrics. The experimental results demonstrate the outstanding performance of our approach on the CNN/DailyMail, XSum, and PubMed datasets, achieving highly competitive results. In particular, our method achieves ROUGE-1 of 44. 65, ROUGE-2 of 21. 32, and ROUGE-L of 40. 87 on the CNN/DailyMail dataset. The outcomes across various evaluation metrics substantiate that the Diverse Oracle extraction algorithm adeptly captures a broader array of sentences with reduced redundancy, consequently enhancing the interpretability of the DCDSum framework.

Authors

• Jiaqi Zhang Amap, China
• Ling Lu
• Liang Zhang Dalian University of Technology
• Yinong Chen
• Wanping Liu

Keywords

• Automatic summarization
• Extractive summarization
• Contrastive learning
• Oracle
• Pre-trained model