{"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-extractive-summarization-by-pre","title":"Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers","arxiv_id":"2010.08242","date":"2020-10-16","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Shusheng Xu","Xingxing Zhang","Yi Wu","Furu Wei","Ming Zhou"],"abstract":"Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights measured by sentence similarities. In this work, we find that transformer attentions can be used to rank sentences for unsupervised extractive summarization. Specifically, we first pre-train a hierarchical transformer model using unlabeled documents only. Then we propose a method to rank sentences using sentence-level self-attentions and pre-training objectives. Experiments on CNN/DailyMail and New York Times datasets show our model achieves state-of-the-art performance on unsupervised summarization. We also find in experiments that our model is less dependent on sentence positions. When using a linear combination of our model and a recent unsupervised model explicitly modeling sentence positions, we obtain even better results.","url_abs":"https://arxiv.org/abs/2010.08242v1","url_pdf":"https://arxiv.org/pdf/2010.08242v1.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-extractive-summarization-by-pre","repo_url":"https://github.com/xssstory/STAS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"extractive-document-summarization-1","task_name":"Extractive Document Summarization"},{"task_slug":"extractive-summarization","task_name":"Extractive Summarization"},{"task_slug":"extractive-document-summarization","task_name":"Extractive Text Summarization"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"unsupervised-extractive-summarization","task_name":"Unsupervised Extractive Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.08242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.08242"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/xssstory/STAS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"d4edf1488a0eb249","entry":"doc2sents","repo":"xssstory/STAS","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/xssstory/STAS/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"d4edf1488a0eb249"}},{"code_sha256_prefix":"0efbc695564f2a8e","entry":"line2sents","repo":"xssstory/STAS","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/xssstory/STAS/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"0efbc695564f2a8e"}},{"code_sha256_prefix":"c9934030622e1adf","entry":"lmap","repo":"xssstory/STAS","repo_kind":"official","path":"ensemble.py","file_url":"https://github.com/xssstory/STAS/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"c9934030622e1adf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}