{"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/scispacy-fast-and-robust-models-for","title":"ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing","arxiv_id":"1902.07669","date":"2019-02-20","proceeding":"WS 2019 8","authors":["Mark Neumann","Daniel King","Iz Beltagy","Waleed Ammar"],"abstract":"Despite recent advances in natural language processing, many statistical models for processing text perform extremely poorly under domain shift. Processing biomedical and clinical text is a critically important application area of natural language processing, for which there are few robust, practical, publicly available models. This paper describes scispaCy, a new tool for practical biomedical/scientific text processing, which heavily leverages the spaCy library. We detail the performance of two packages of models released in scispaCy and demonstrate their robustness on several tasks and datasets. Models and code are available at https://allenai.github.io/scispacy/","url_abs":"https://arxiv.org/abs/1902.07669v3","url_pdf":"https://arxiv.org/pdf/1902.07669v3.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":"scispacy-fast-and-robust-models-for","repo_url":"https://github.com/allenai/scispacy","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.07669"}},"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/scispacy","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"38e0c973a4edfbda","entry":"cached_path","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/file_cache.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/file_cache.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":"38e0c973a4edfbda"}},{"code_sha256_prefix":"5b5f3885feae8e80","entry":"filename_to_url","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/file_cache.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/file_cache.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":"5b5f3885feae8e80"}},{"code_sha256_prefix":"21657ab6fe37fcec","entry":"process_example","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/data_util.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/data_util.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":"21657ab6fe37fcec"}},{"code_sha256_prefix":"08b83e08022fef37","entry":"remove_new_lines","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/custom_tokenizer.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/custom_tokenizer.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":"08b83e08022fef37"}},{"code_sha256_prefix":"b6927585ad29f738","entry":"remove_overlapping_entities","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/data_util.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/data_util.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":"b6927585ad29f738"}},{"code_sha256_prefix":"b9b3cbcc3d52b7fe","entry":"select_subset_of_overlapping_chain","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/data_util.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/data_util.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":"b9b3cbcc3d52b7fe"}},{"code_sha256_prefix":"c84ecd1eb5ee2729","entry":"url_to_filename","repo":"allenai/scispacy","repo_kind":"official","path":"scispacy/file_cache.py","file_url":"https://github.com/allenai/scispacy/blob/HEAD/scispacy/file_cache.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":"c84ecd1eb5ee2729"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}