{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/unsupervised-summarization-re-ranking","title":"Unsupervised Summarization Re-ranking","arxiv_id":"2212.09593","date":"2022-12-19","proceeding":null,"authors":["Mathieu Ravaut","Shafiq Joty","Nancy Chen"],"abstract":"With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags significantly behind their supervised counterparts. Similarly to the supervised setup, we notice a very high variance in quality among summary candidates from these models while only one candidate is kept as the summary output. In this paper, we propose to re-rank summary candidates in an unsupervised manner, aiming to close the performance gap between unsupervised and supervised models. Our approach improves the unsupervised PEGASUS by up to 7.27% and ChatGPT by up to 6.86% relative mean ROUGE across four widely-adopted summarization benchmarks ; and achieves relative gains of 7.51% (up to 23.73% from XSum to WikiHow) averaged over 30 zero-shot transfer setups (finetuning on a dataset, evaluating on another).","url_abs":"https://arxiv.org/abs/2212.09593v4","url_pdf":"https://arxiv.org/pdf/2212.09593v4.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":"unsupervised-summarization-re-ranking","repo_url":"https://github.com/ntunlp/summscore","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unsupervised-summarization-re-ranking","repo_url":"https://github.com/ntunlp/summscore-acl-findings-2023","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"re-ranking","task_name":"Re-Ranking"}],"methods":[{"method_slug":"pegasus","method_name":"PEGASUS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}