A New Approach to Overgenerating and Scoring Abstractive Summaries

Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu


Abstract
We propose a new approach to generate multiple variants of the target summary with diverse content and varying lengths, then score and select admissible ones according to users’ needs. Abstractive summarizers trained on single reference summaries may struggle to produce outputs that achieve multiple desirable properties, i.e., capturing the most important information, being faithful to the original, grammatical and fluent. In this paper, we propose a two-staged strategy to generate a diverse set of candidate summaries from the source text in stage one, then score and select admissible ones in stage two. Importantly, our generator gives a precise control over the length of the summary, which is especially well-suited when space is limited. Our selectors are designed to predict the optimal summary length and put special emphasis on faithfulness to the original text. Both stages can be effectively trained, optimized and evaluated. Our experiments on benchmark summarization datasets suggest that this paradigm can achieve state-of-the-art performance.
Anthology ID:
2021.naacl-main.110
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1392–1404
Language:
URL:
https://aclanthology.org/2021.naacl-main.110
DOI:
10.18653/v1/2021.naacl-main.110
Bibkey:
Cite (ACL):
Kaiqiang Song, Bingqing Wang, Zhe Feng, and Fei Liu. 2021. A New Approach to Overgenerating and Scoring Abstractive Summaries. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1392–1404, Online. Association for Computational Linguistics.
Cite (Informal):
A New Approach to Overgenerating and Scoring Abstractive Summaries (Song et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.110.pdf
Video:
 https://aclanthology.org/2021.naacl-main.110.mp4
Code
 ucfnlp/varying-length-summ
Data
NEWSROOM