{"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/ms2-multi-document-summarization-of-medical","title":"MS2: Multi-Document Summarization of Medical Studies","arxiv_id":"2104.06486","date":"2021-04-13","proceeding":null,"authors":["Jay DeYoung","Iz Beltagy","Madeleine van Zuylen","Bailey Kuehl","Lucy Lu Wang"],"abstract":"To assess the effectiveness of any medical intervention, researchers must conduct a time-intensive and highly manual literature review. NLP systems can help to automate or assist in parts of this expensive process. In support of this goal, we release MS^2 (Multi-Document Summarization of Medical Studies), a dataset of over 470k documents and 20k summaries derived from the scientific literature. This dataset facilitates the development of systems that can assess and aggregate contradictory evidence across multiple studies, and is the first large-scale, publicly available multi-document summarization dataset in the biomedical domain. We experiment with a summarization system based on BART, with promising early results. We formulate our summarization inputs and targets in both free text and structured forms and modify a recently proposed metric to assess the quality of our system's generated summaries. Data and models are available at https://github.com/allenai/ms2","url_abs":"https://arxiv.org/abs/2104.06486v3","url_pdf":"https://arxiv.org/pdf/2104.06486v3.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":"ms2-multi-document-summarization-of-medical","repo_url":"https://github.com/allenai/ms2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"ms2-multi-document-summarization-of-medical","repo_url":"https://github.com/allenai/mslr-shared-task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"document-summarization","task_name":"Document Summarization"},{"task_slug":"multi-document-summarization","task_name":"Multi-Document Summarization"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[{"slug":"ms-2","name":"MS^2","full_name":"Multi-Document Summarization of Medical Studies"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.06486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06486"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/mslr-shared-task","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/allenai/ms2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":1,"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":0,"samples":[{"code_sha256_prefix":"74c2790489a843b9","entry":"get_tokenizer","repo":"allenai/ms2","repo_kind":"official","path":"ms2/utils.py","file_url":"https://github.com/allenai/ms2/blob/HEAD/ms2/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74c2790489a843b9"}},{"code_sha256_prefix":"4b39ea742ad05097","entry":"jsd","repo":"allenai/mslr-shared-task","repo_kind":"listed","path":"ms2/evaluation/utils.py","file_url":"https://github.com/allenai/mslr-shared-task/blob/HEAD/ms2/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b39ea742ad05097"}},{"code_sha256_prefix":"755e8f3e5bcd963a","entry":"pad_tensors","repo":"allenai/ms2","repo_kind":"official","path":"ms2/models/utils.py","file_url":"https://github.com/allenai/ms2/blob/HEAD/ms2/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"755e8f3e5bcd963a"}},{"code_sha256_prefix":"a5d2696481d31b52","entry":"read_jsonl","repo":"allenai/ms2","repo_kind":"official","path":"ms2/models/pubmed_tagger.py","file_url":"https://github.com/allenai/ms2/blob/HEAD/ms2/models/pubmed_tagger.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5d2696481d31b52"}},{"code_sha256_prefix":"cc79919afd15bd73","entry":"rouge_scores","repo":"allenai/ms2","repo_kind":"official","path":"ms2/models/utils.py","file_url":"https://github.com/allenai/ms2/blob/HEAD/ms2/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc79919afd15bd73"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}