{"url":"/task/extractive-document-summarization-1","name":"Extractive Document Summarization","slug":"extractive-document-summarization-1","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":12,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/cnn-daily-mail-1","name":"CNN/Daily Mail","full_name":"CNN/Daily Mail","num_papers_in_archive":530},{"url":"/dataset/subsume","name":"SubSumE","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":12,"of":12,"tagged_in_all":29,"items":[{"url":"/paper/text-summarization-with-pretrained-encoders","title":"Text Summarization with Pretrained Encoders","date":"2019-08-22","arxiv_id":"1908.08345","repositories_listed":19,"syntology":{"n":21,"n_ran":7,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/fine-tune-bert-for-extractive-summarization","title":"Fine-tune BERT for Extractive Summarization","date":"2019-03-25","arxiv_id":"1903.10318","repositories_listed":12,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/aredsum-adaptive-redundancy-aware-iterative","title":"AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization","date":"2020-04-13","arxiv_id":"2004.06176","repositories_listed":3,"syntology":null},{"url":"/paper/tap-dlnd-10-a-corpus-for-document-level","title":"TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection","date":"2018-02-20","arxiv_id":"1802.06950","repositories_listed":2,"syntology":null},{"url":"/paper/gosum-extractive-summarization-of-long","title":"GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state","date":"2022-11-18","arxiv_id":"2211.10247","repositories_listed":1,"syntology":null},{"url":"/paper/gusum-graph-based-unsupervised-summarization-1","title":"GUSUM: Graph-based Unsupervised Summarization Using Sentence Features Scoring and Sentence-BERT","date":"2022-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dimsum-distributed-and-multilingual","title":"DiMSum: Distributed and Multilingual Summarization of Financial Narratives","date":"2022-06-01","arxiv_id":null,"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/heterogeneous-graph-neural-networks-for-1","title":"Heterogeneous Graph Neural Networks for Extractive Document Summarization","date":"2020-04-26","arxiv_id":"2004.12393","repositories_listed":1,"syntology":null},{"url":"/paper/deepchannel-salience-estimation-by","title":"DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization","date":"2018-11-06","arxiv_id":"1811.02394","repositories_listed":1,"syntology":null},{"url":"/paper/neural-document-summarization-by-jointly","title":"Neural Document Summarization by Jointly Learning to Score and Select Sentences","date":"2018-07-06","arxiv_id":"1807.02305","repositories_listed":1,"syntology":null},{"url":"/paper/document-modeling-with-external-attention-for","title":"Document Modeling with External Attention for Sentence Extraction","date":"2018-07-01","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"}}