Papers › Salience Allocation as Guidance for Abstractive Summarization

Salience Allocation as Guidance for Abstractive Summarization

22 Oct 2022arXiv:2210.12330archive 2025-07-28

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

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 vary, 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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tencent-ailab/season officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Abstractive Text SummarizationArticles

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Abstractive Text Summarization CNN / Daily Mail SEASON ROUGE-1 46.27 #7 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail SEASON ROUGE-2 22.64 #7 of 53 Archive leaderboard report
Abstractive Text Summarization CNN / Daily Mail SEASON ROUGE-L 43.08 #7 of 53 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections