Multi-Reward Reinforced Summarization with Saliency and Entailment

Ramakanth Pasunuru, Mohit Bansal


Abstract
Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy. In this work, we address these three important aspects of a good summary via a reinforcement learning approach with two novel reward functions: ROUGESal and Entail, on top of a coverage-based baseline. The ROUGESal reward modifies the ROUGE metric by up-weighting the salient phrases/words detected via a keyphrase classifier. The Entail reward gives high (length-normalized) scores to logically-entailed summaries using an entailment classifier. Further, we show superior performance improvement when these rewards are combined with traditional metric (ROUGE) based rewards, via our novel and effective multi-reward approach of optimizing multiple rewards simultaneously in alternate mini-batches. Our method achieves the new state-of-the-art results on CNN/Daily Mail dataset as well as strong improvements in a test-only transfer setup on DUC-2002.
Anthology ID:
N18-2102
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
646–653
Language:
URL:
https://aclanthology.org/N18-2102
DOI:
10.18653/v1/N18-2102
Bibkey:
Cite (ACL):
Ramakanth Pasunuru and Mohit Bansal. 2018. Multi-Reward Reinforced Summarization with Saliency and Entailment. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 646–653, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Multi-Reward Reinforced Summarization with Saliency and Entailment (Pasunuru & Bansal, NAACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/N18-2102.pdf
Data
CNN/Daily MailMultiNLISQuAD