Salience Allocation as Guidance for Abstractive Summarization
Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen
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.
BibTeX
@inproceedings{wang-etal-2022-salience,
title = "Salience Allocation as Guidance for Abstractive Summarization",
author = "Wang, Fei and
Song, Kaiqiang and
Zhang, Hongming and
Jin, Lifeng and
Cho, Sangwoo and
Yao, Wenlin and
Wang, Xiaoyang and
Chen, Muhao and
Yu, Dong",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.409/",
doi = "10.18653/v1/2022.emnlp-main.409",
pages = "6094--6106"
}