{"url":"/task/unsupervised-extractive-summarization","name":"Unsupervised Extractive Summarization","slug":"unsupervised-extractive-summarization","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":30,"papers_with_code":18,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-extractive-summarization-on","slug":"unsupervised-extractive-summarization-on","dataset":"arXiv Summarization Dataset","dataset_url":"/dataset/arxiv-summarization-dataset","rows_in_archive":10,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"FAR","paper_title":"Improving Unsupervised Extractive Summarization with Facet-Aware Modeling","paper_url":"/paper/improving-unsupervised-extractive","paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-extractive-summarization-on-1","slug":"unsupervised-extractive-summarization-on-1","dataset":"Pubmed","dataset_url":"/dataset/pubmed","rows_in_archive":9,"metrics":["ROUGE-1","ROUGE-2","ROUGE-L"],"first_row_in_archive_order":{"model":"HipoRank","paper_title":"Discourse-Aware Unsupervised Summarization of Long Scientific Documents","paper_url":"/paper/hiporank-incorporating-hierarchical-and","paper_date":"2020-05-01","arxiv_id":"2005.00513","code_links":[{"title":"mirandrom/HipoRank","url":"https://github.com/mirandrom/HipoRank"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-extractive-summarization-on-2","slug":"unsupervised-extractive-summarization-on-2","dataset":"FacetSum","dataset_url":"/dataset/facetsum","rows_in_archive":5,"metrics":["ROUGE-L"],"first_row_in_archive_order":{"model":"HipoRank","paper_title":"Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents","paper_url":"/paper/bringing-structure-into-summaries-a-faceted","paper_date":"2021-05-31","arxiv_id":"2106.00130","code_links":[{"title":"hfthair/emerald_crawler","url":"https://github.com/hfthair/emerald_crawler"},{"title":"bnitsan/papertweet","url":"https://github.com/bnitsan/papertweet"}],"syntology":null}}],"datasets":[{"url":"/dataset/pubmed","name":"Pubmed","full_name":"","num_papers_in_archive":1236},{"url":"/dataset/arxiv-summarization-dataset","name":"arXiv Summarization Dataset","full_name":"","num_papers_in_archive":13},{"url":"/dataset/facetsum","name":"FacetSum","full_name":"","num_papers_in_archive":4},{"url":"/dataset/xwikiref","name":"XWikiRef","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/summarization","name":"Summarization"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":18,"of":18,"tagged_in_all":30,"items":[{"url":"/paper/a-discourse-aware-attention-model-for","title":"A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents","date":"2018-04-16","arxiv_id":"1804.05685","repositories_listed":3,"syntology":{"n":14,"n_ran":1,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/unsupervised-extractive-dialogue","title":"Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space","date":"2024-05-16","arxiv_id":"2405.09765","repositories_listed":2,"syntology":null},{"url":"/paper/bringing-structure-into-summaries-a-faceted","title":"Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents","date":"2021-05-31","arxiv_id":"2106.00130","repositories_listed":2,"syntology":null},{"url":"/paper/bipartite-graph-pre-training-for-unsupervised","title":"Bipartite Graph Pre-training for Unsupervised Extractive Summarization with Graph Convolutional Auto-Encoders","date":"2023-10-29","arxiv_id":"2310.18992","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-extractive-summarization-of","title":"Unsupervised Extractive Summarization of Emotion Triggers","date":"2023-06-02","arxiv_id":"2306.01444","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/xwikigen-cross-lingual-summarization-for","title":"XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages","date":"2023-03-22","arxiv_id":"2303.12308","repositories_listed":1,"syntology":null},{"url":"/paper/improving-sentence-similarity-estimation-for","title":"Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization","date":"2023-02-24","arxiv_id":"2302.12490","repositories_listed":1,"syntology":null},{"url":"/paper/computing-and-exploiting-document-structure","title":"Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions","date":"2022-11-06","arxiv_id":"2211.03229","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-trade-off-between-redundancy-and-local","title":"On the Trade-off between Redundancy and Local Coherence in Summarization","date":"2022-05-20","arxiv_id":"2205.10192","repositories_listed":1,"syntology":null},{"url":"/paper/tweetsumm-a-dialog-summarization-dataset-for-1","title":"TWEETSUMM -- A Dialog Summarization Dataset for Customer Service","date":"2021-11-23","arxiv_id":"2111.11894","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-extractive-summarization-based","title":"Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-extractive-summarization-using","title":"Unsupervised Extractive Summarization using Pointwise Mutual Information","date":"2021-02-11","arxiv_id":"2102.06272","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-abstractive-summarization-of","title":"Unsupervised Abstractive Summarization of Bengali Text Documents","date":"2021-01-26","arxiv_id":"2102.04490","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-extractive-summarization-by-pre","title":"Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers","date":"2020-10-16","arxiv_id":"2010.08242","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/hiporank-incorporating-hierarchical-and","title":"Discourse-Aware Unsupervised Summarization of Long Scientific Documents","date":"2020-05-01","arxiv_id":"2005.00513","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-centrality-revisited-for","title":"Sentence Centrality Revisited for Unsupervised Summarization","date":"2019-06-08","arxiv_id":"1906.03508","repositories_listed":1,"syntology":null},{"url":"/paper/190600424","title":"Plain English Summarization of Contracts","date":"2019-06-02","arxiv_id":"1906.00424","repositories_listed":1,"syntology":null},{"url":"/paper/combining-graph-degeneracy-and-submodularity","title":"Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization","date":"2017-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}