Salience Allocation as Guidance for Abstractive Summarization

Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu


Abstract
Abstractive summarization models typically learn to capture the salient information from scratch implicitly.Recent literature adds extractive summaries as guidance for abstractive summarization models to provide hints of salient content and achieves better performance.However, extractive summaries as guidance could be over strict, leading to information loss or noisy signals.Furthermore, it cannot easily adapt to documents with various abstractiveness.As the number and allocation of salience content pieces varies, it is hard to find a fixed threshold deciding which content should be included in the guidance.In this paper, we propose a novel summarization approach with a flexible and reliable salience guidance, namely SEASON (SaliencE Allocation as Guidance for Abstractive SummarizatiON).SEASON utilizes the allocation of salience expectation to guide abstractive summarization and adapts well to articles in different abstractiveness.Automatic and human evaluations on two benchmark datasets show that the proposed method is effective and reliable.Empirical results on more than one million news articles demonstrate a natural fifteen-fifty salience split for news article sentences, providing a useful insight for composing news articles.
Anthology ID:
2022.emnlp-main.409
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6094–6106
Language:
URL:
https://aclanthology.org/2022.emnlp-main.409
DOI:
10.18653/v1/2022.emnlp-main.409
Bibkey:
Cite (ACL):
Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, and Dong Yu. 2022. Salience Allocation as Guidance for Abstractive Summarization. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6094–6106, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Salience Allocation as Guidance for Abstractive Summarization (Wang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.409.pdf