Using Question Answering Rewards to Improve Abstractive Summarization

Chulaka Gunasekara, Guy Feigenblat, Benjamin Sznajder, Ranit Aharonov, Sachindra Joshi


Abstract
Neural abstractive summarization models have drastically improved in the recent years. However, the summaries generated by these models generally suffer from issues such as: not capturing the critical facts in source documents, and containing facts that are inconsistent with the source documents. In this work, we present a general framework to train abstractive summarization models to alleviate such issues. We first train a sequence-to-sequence model to summarize documents, and then further train this model in a Reinforcement Learning setting with question-answering based rewards. We evaluate the summaries generated by the this framework using multiple automatic measures and human judgements. The experimental results show that the question-answering rewards can be used as a general framework to improve neural abstractive summarization. Particularly, the results from human evaluations show that the summaries generated by our approach is preferred over 30% of the time over the summaries generated by general abstractive summarization models.
Anthology ID:
2021.findings-emnlp.47
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
518–526
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.47
DOI:
10.18653/v1/2021.findings-emnlp.47
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.47.pdf