Papers › Convex Aggregation for Opinion Summarization

Convex Aggregation for Opinion Summarization

3 Apr 2021Findings (EMNLP) 2021 11arXiv:2104.01371archive 2025-07-28

Hayate Iso, Xiaolan Wang, Yoshihiko Suhara, Stefanos Angelidis, Wang-Chiew Tan

Recent advances in text autoencoders have significantly improved the quality of the latent space, which enables models to generate grammatical and consistent text from aggregated latent vectors. As a successful application of this property, unsupervised opinion summarization models generate a summary by decoding the aggregated latent vectors of inputs. More specifically, they perform the aggregation via simple average. However, little is known about how the vector aggregation step affects the generation quality. In this study, we revisit the commonly used simple average approach by examining the latent space and generated summaries. We found that text autoencoders tend to generate overly generic summaries from simply averaged latent vectors due to an unexpected L₂-norm shrinkage in the aggregated latent vectors, which we refer to as summary vector degeneration. To overcome this issue, we develop a framework Coop, which searches input combinations for the latent vector aggregation using input-output word overlap. Experimental results show that Coop successfully alleviates the summary vector degeneration issue and establishes new state-of-the-art performance on two opinion summarization benchmarks. Code is available at https://github.com/megagonlabs/coop.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

megagonlabs/coop officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization (arXiv:1810.05739; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Opinion SummarizationUnsupervised Opinion Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Opinion Summarization Amazon BiMeanVAE - Coop ROUGE-1 36.57 #1 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon BiMeanVAE - Coop ROUGE-2 7.23 #1 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon BiMeanVAE - Coop ROUGE-L 21.24 #1 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon Optimus - Coop ROUGE-1 35.32 #2 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon Optimus - Coop ROUGE-2 6.22 #2 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon Optimus - Coop ROUGE-L 19.84 #2 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon BiMeanVAE - SimpleAvg ROUGE-1 33.6 #3 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon BiMeanVAE - SimpleAvg ROUGE-2 6.64 #3 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon BiMeanVAE - SimpleAvg ROUGE-L 20.87 #3 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon Optimus - SimpleAvg ROUGE-1 33.54 #4 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon Optimus - SimpleAvg ROUGE-2 6.18 #4 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Amazon Optimus - SimpleAvg ROUGE-L 19.34 #4 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp BiMeanVAE - Coop ROUGE-1 35.37 #1 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp BiMeanVAE - Coop ROUGE-2 7.35 #1 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp BiMeanVAE - Coop ROUGE-L 19.94 #1 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp Optimus - Coop ROUGE-1 33.68 #2 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp Optimus - Coop ROUGE-2 7 #2 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp Optimus - Coop ROUGE-L 18.95 #2 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp BiMeanVAE - SimpleAvg ROUGE-1 32.87 #3 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp BiMeanVAE - SimpleAvg ROUGE-2 6.93 #3 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp BiMeanVAE - SimpleAvg ROUGE-L 19.89 #3 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp Optimus - SimpleAvg ROUGE-1 31.23 #4 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp Optimus - SimpleAvg ROUGE-2 6.48 #4 of 4 Archive leaderboard report
Unsupervised Opinion Summarization Yelp Optimus - SimpleAvg ROUGE-L 18.27 #4 of 4 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