Papers › Systematically Exploring Redundancy Reduction in Summarizing Long Documents

Systematically Exploring Redundancy Reduction in Summarizing Long Documents

30 Nov 2020Asian Chapter of the Association for Computational Linguistics 2020arXiv:2012.00052archive 2025-07-28

Wen Xiao, Giuseppe Carenini

Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents. Yet, redundancy reduction has not been thoroughly investigated in neural summarization. In this work, we systematically explore and compare different ways to deal with redundancy when summarizing long documents. Specifically, we organize the existing methods into categories based on when and how the redundancy is considered. Then, in the context of these categories, we propose three additional methods balancing non-redundancy and importance in a general and flexible way. In a series of experiments, we show that our proposed methods achieve the state-of-the-art with respect to ROUGE scores on two scientific paper datasets, Pubmed and arXiv, while reducing redundancy significantly.

PaperPDFConference PDFCode

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

Code

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 Arxiv HEP-TH citation graph ExtSum-LG+RdLoss ROUGE-1 44.01 #17 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph ExtSum-LG+RdLoss ROUGE-2 17.79 #17 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph ExtSum-LG+RdLoss ROUGE-L 39.09 #17 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph ExtSum-LG+MMR-Select+ ROUGE-1 43.87 #18 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph ExtSum-LG+MMR-Select+ ROUGE-2 17.5 #18 of 28 Archive leaderboard report
Text Summarization Arxiv HEP-TH citation graph ExtSum-LG+MMR-Select+ ROUGE-L 38.97 #18 of 28 Archive leaderboard report
Text Summarization Pubmed ExtSum-LG+MMR-Select+ ROUGE-1 45.39 #16 of 29 Archive leaderboard report
Text Summarization Pubmed ExtSum-LG+MMR-Select+ ROUGE-2 20.37 #16 of 29 Archive leaderboard report
Text Summarization Pubmed ExtSum-LG+MMR-Select+ ROUGE-L 40.99 #16 of 29 Archive leaderboard report
Text Summarization Pubmed ExtSum-LG+RdLoss ROUGE-1 45.3 #17 of 29 Archive leaderboard report
Text Summarization Pubmed ExtSum-LG+RdLoss ROUGE-2 20.42 #17 of 29 Archive leaderboard report
Text Summarization Pubmed ExtSum-LG+RdLoss ROUGE-L 40.95 #17 of 29 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