Papers › Searching for Effective Neural Extractive Summarization: What Works and What's Next

Searching for Effective Neural Extractive Summarization: What Works and What's Next

8 Jul 2019ACL 2019 7arXiv:1907.03491archive 2025-07-28

Ming Zhong, PengFei Liu, Danqing Wang, Xipeng Qiu, Xuanjing Huang

The recent years have seen remarkable success in the use of deep neural networks on text summarization. However, there is no clear understanding of \textit{why} they perform so well, or \textit{how} they might be improved. In this paper, we seek to better understand how neural extractive summarization systems could benefit from different types of model architectures, transferable knowledge and learning schemas. Additionally, we find an effective way to improve current frameworks and achieve the state-of-the-art result on CNN/DailyMail by a large margin based on our observations and analyses. Hopefully, our work could provide more clues for future research on extractive summarization.

PaperPDFConference PDFCode

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

Code

zhdbwe/Paper-DailyReading mentioned on GitHubtf 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

Extractive SummarizationExtractive Text SummarizationText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Extractive Text Summarization CNN / Daily Mail PNBERT ROUGE-1 42.69 #7 of 15 Archive leaderboard report
Extractive Text Summarization CNN / Daily Mail PNBERT ROUGE-2 19.60 #7 of 15 Archive leaderboard report
Extractive Text Summarization CNN / Daily Mail PNBERT ROUGE-L 38.85 #7 of 15 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