Papers › Simple Unsupervised Summarization by Contextual Matching

Simple Unsupervised Summarization by Contextual Matching

31 Jul 2019ACL 2019 7arXiv:1907.13337archive 2025-07-28

Jiawei Zhou, Alexander M. Rush

We propose an unsupervised method for sentence summarization using only language modeling. The approach employs two language models, one that is generic (i.e. pretrained), and the other that is specific to the target domain. We show that by using a product-of-experts criteria these are enough for maintaining continuous contextual matching while maintaining output fluency. Experiments on both abstractive and extractive sentence summarization data sets show promising results of our method without being exposed to any paired data.

PaperPDFConference PDFCode

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

Code

jzhou316/Unsupervised-Sentence-Summarization 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

Language ModelingLanguage ModellingSentenceSentence SummarizationText SummarizationUnsupervised Sentence Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization GigaWord Contextual Match ROUGE-1 26.48 #41 of 41 Archive leaderboard report
Text Summarization GigaWord Contextual Match ROUGE-2 10.05 #41 of 41 Archive leaderboard report
Text Summarization GigaWord Contextual Match ROUGE-L 24.41 #41 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