{"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/memsum-extractive-summarization-of-long","title":"MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes","arxiv_id":"2107.08929","date":"2021-07-19","proceeding":"ACL 2022 5","authors":["Nianlong Gu","Elliott Ash","Richard H. R. Hahnloser"],"abstract":"We introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at each step with information on the current extraction history. When MemSum iteratively selects sentences into the summary, it considers a broad information set that would intuitively also be used by humans in this task: 1) the text content of the sentence, 2) the global text context of the rest of the document, and 3) the extraction history consisting of the set of sentences that have already been extracted. With a lightweight architecture, MemSum obtains state-of-the-art test-set performance (ROUGE) in summarizing long documents taken from PubMed, arXiv, and GovReport. Ablation studies demonstrate the importance of local, global, and history information. A human evaluation confirms the high quality and low redundancy of the generated summaries, stemming from MemSum's awareness of extraction history.","url_abs":"https://arxiv.org/abs/2107.08929v2","url_pdf":"https://arxiv.org/pdf/2107.08929v2.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":"memsum-extractive-summarization-of-long","repo_url":"https://github.com/nianlonggu/memsum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/extractive-text-summarization-on-govreport","task":"Extractive Text Summarization","dataset":"GovReport","model":"MemSum (extractive)","rank_in_archive_order":1,"of":2,"metrics":{"Avg. Test Rouge1":"59.43","Avg. Test Rouge2":"28.60","Avg. Test RougeLsum":"56.69"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-arxiv","task":"Text Summarization","dataset":"Arxiv HEP-TH citation graph","model":"MemSum (extractive)","rank_in_archive_order":8,"of":28,"metrics":{"ROUGE-1":"48.42","ROUGE-2":"20.30","ROUGE-L":"42.54"},"uses_additional_data":false},{"leaderboard":"/sota/text-summarization-on-pubmed-1","task":"Text Summarization","dataset":"Pubmed","model":"MemSum (extractive)","rank_in_archive_order":7,"of":29,"metrics":{"ROUGE-1":"49.25","ROUGE-2":"22.94","ROUGE-L":"44.42"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.08929","atlas_url":"https://app.syntology.ai/?focus=2107.08929","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":"2107.08929"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.08929\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.08929"},"call":"get_concepts_for_paper(arxiv_id=\"2107.08929\")"}],"by_repo":[{"repo":"nianlonggu/memsum","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"f01ba22f438a74e784fb8fe71cca58f5fa58af251e5ecb17942bf1048d1bbdcb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}