Papers › A New Approach to Overgenerating and Scoring Abstractive Summaries

A New Approach to Overgenerating and Scoring Abstractive Summaries

5 Apr 2021NAACL 2021 4arXiv:2104.01726archive 2025-07-28

Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu

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.

PaperPDFConference PDFCode

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

Code

ucfnlp/varying-length-summ officialmentioned in paperpytorch 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

Text Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization GigaWord Best Summary Length ROUGE-1 39.27 #12 of 41 Archive leaderboard report
Text Summarization GigaWord Best Summary Length ROUGE-2 20.40 #12 of 41 Archive leaderboard report
Text Summarization GigaWord Best Summary Length ROUGE-L 37.75 #12 of 41 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