{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/convex-aggregation-for-opinion-summarization","title":"Convex Aggregation for Opinion Summarization","arxiv_id":"2104.01371","date":"2021-04-03","proceeding":"Findings (EMNLP) 2021 11","authors":["Hayate Iso","Xiaolan Wang","Yoshihiko Suhara","Stefanos Angelidis","Wang-Chiew Tan"],"abstract":"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 $L_2$-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 \\url{https://github.com/megagonlabs/coop}.","url_abs":"https://arxiv.org/abs/2104.01371v3","url_pdf":"https://arxiv.org/pdf/2104.01371v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"convex-aggregation-for-opinion-summarization","repo_url":"https://github.com/megagonlabs/coop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"opinion-summarization","task_name":"Opinion Summarization"},{"task_slug":"unsupervised-opinion-summarization","task_name":"Unsupervised Opinion Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-opinion-summarization-on-amazon","task":"Unsupervised Opinion Summarization","dataset":"Amazon","model":"BiMeanVAE - Coop","rank_in_archive_order":1,"of":4,"metrics":{"ROUGE-1":"36.57","ROUGE-2":"7.23","ROUGE-L":"21.24"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-amazon","task":"Unsupervised Opinion Summarization","dataset":"Amazon","model":"Optimus - Coop","rank_in_archive_order":2,"of":4,"metrics":{"ROUGE-1":"35.32","ROUGE-2":"6.22","ROUGE-L":"19.84"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-amazon","task":"Unsupervised Opinion Summarization","dataset":"Amazon","model":"BiMeanVAE - SimpleAvg","rank_in_archive_order":3,"of":4,"metrics":{"ROUGE-1":"33.6","ROUGE-2":"6.64","ROUGE-L":"20.87"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-amazon","task":"Unsupervised Opinion Summarization","dataset":"Amazon","model":"Optimus - SimpleAvg","rank_in_archive_order":4,"of":4,"metrics":{"ROUGE-1":"33.54","ROUGE-2":"6.18","ROUGE-L":"19.34"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-yelp","task":"Unsupervised Opinion Summarization","dataset":"Yelp","model":"BiMeanVAE - Coop","rank_in_archive_order":1,"of":4,"metrics":{"ROUGE-1":"35.37","ROUGE-2":"7.35","ROUGE-L":"19.94"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-yelp","task":"Unsupervised Opinion Summarization","dataset":"Yelp","model":"Optimus - Coop","rank_in_archive_order":2,"of":4,"metrics":{"ROUGE-1":"33.68","ROUGE-2":"7","ROUGE-L":"18.95"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-yelp","task":"Unsupervised Opinion Summarization","dataset":"Yelp","model":"BiMeanVAE - SimpleAvg","rank_in_archive_order":3,"of":4,"metrics":{"ROUGE-1":"32.87","ROUGE-2":"6.93","ROUGE-L":"19.89"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-opinion-summarization-on-yelp","task":"Unsupervised Opinion Summarization","dataset":"Yelp","model":"Optimus - SimpleAvg","rank_in_archive_order":4,"of":4,"metrics":{"ROUGE-1":"31.23","ROUGE-2":"6.48","ROUGE-L":"18.27"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.01371","atlas_url":"https://app.syntology.ai/?focus=2104.01371","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2104.01371"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.01371\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.01371"},"call":"get_concepts_for_paper(arxiv_id=\"2104.01371\")"}],"by_repo":[{"repo":"megagonlabs/coop","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1810.05739"],"harvested_for_calls":[{"arxiv_id":"1810.05739","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.05739"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.05739\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c63a1bf5c0788b3213cc0b78759bb1fbc319ac25c255b4e02e7920c0040a2cb2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}