Author:
Xiao Liqiang,Wang Lu,He Hao,Jin Yaohui
Abstract
Jointly using the extractive and abstractive summarization methods can combine their complementary advantages, generating both informative and concise summary. Existing methods that adopt an extract-then-abstract strategy have achieved impressive results, yet they suffer from the information loss in the abstraction step because they compress all the selected sentences without distinguish. Especially when the whole sentence is summary-worthy, salient content would be lost by compression. To address this problem, we propose HySum, a hybrid framework for summarization that can flexibly switch between copying sentence and rewriting sentence according to the degree of redundancy. In this way, our approach can effectively combine the advantages of two branches of summarization, juggling informativity and conciseness. Moreover, we based on Hierarchical Reinforcement Learning, propose an end-to-end reinforcing method to bridge together the extraction module and rewriting module, which can enhance the cooperation between them. Automatic evaluation shows that our approach significantly outperforms the state-of-the-arts on the CNN/DailyMail corpus. Human evaluation also demonstrates that our generated summaries are more informative and concise than popular models.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. SentMask: A Sentence-Aware Mask Attention-Guided Two-Stage Text Summarization Component;International Journal of Intelligent Systems;2023-08-22
2. Deep Reinforcement Learning with Copy-oriented Context Awareness and Weighted Rewards for Abstractive Summarization;Proceedings of the 2023 2nd Asia Conference on Algorithms, Computing and Machine Learning;2023-03-17
3. A General Contextualized Rewriting Framework for Text Summarization;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2023
4. Cross-Domain Reinforcement Learning for Sentiment Analysis;Communications in Computer and Information Science;2023
5. Can PoW Consensus Protocol Resist the Whale Attack?;2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS);2022-12