{"id":"https://openalex.org/W2915623326","doi":"https://doi.org/10.18653/v1/w19-5034","title":"ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing","display_name":"ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2915623326","doi":"https://doi.org/10.18653/v1/w19-5034","mag":"2915623326"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-5034","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5034","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/w19-5034","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mark Neumann","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mark Neumann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel King","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel King","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Iz Beltagy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iz Beltagy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Waleed Ammar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Waleed Ammar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.0008,"has_fulltext":false,"cited_by_count":454,"citation_normalized_percentile":{"value":0.99361097,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6528000235557556},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5881999731063843},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4377000033855438},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43369999527931213},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.42080000042915344},{"id":"https://openalex.org/keywords/natural-language-user-interface","display_name":"Natural language user interface","score":0.40070000290870667},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3804999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023999929428101},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6528000235557556},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655999779701233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5235000252723694},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3467999994754791},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C7044111","wikidata":"https://www.wikidata.org/wiki/Q15844891","display_name":"Temporal annotation","level":5,"score":0.32589998841285706},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.2549999952316284},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w19-5034","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5034","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.07669","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.07669","pdf_url":"https://arxiv.org/pdf/1902.07669","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-5034","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-5034","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th BioNLP Workshop and Shared Task","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,72],"natural":[4,31],"language":[5,32],"processing,":[6,33,55],"many":[7],"statistical":[8],"models":[9,70],"for":[10,34,51],"processing":[11],"text":[12,23,54],"perform":[13],"extremely":[14],"poorly":[15],"under":[16],"domain":[17],"shift.":[18],"Processing":[19],"biomedical":[20],"and":[21,74,81,84],"clinical":[22],"is":[24],"a":[25,48],"critically":[26],"important":[27],"application":[28],"area":[29],"of":[30,66,69],"which":[35,56],"there":[36],"are":[37,86],"few":[38],"robust,":[39],"practical,":[40],"publicly":[41],"available":[42,87],"models.":[43],"This":[44],"paper":[45],"describes":[46],"scispaCy,":[47],"new":[49],"tool":[50],"practical":[52],"biomedical/scientific":[53],"heavily":[57],"leverages":[58],"the":[59,64],"spaCy":[60],"library.":[61],"We":[62],"detail":[63],"performance":[65],"two":[67],"packages":[68],"released":[71],"scispaCy":[73],"demonstrate":[75],"their":[76],"robustness":[77],"on":[78],"several":[79],"tasks":[80],"datasets.":[82],"Models":[83],"code":[85],"at":[88],"https://allenai.github.io/scispacy/":[89]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":90},{"year":2024,"cited_by_count":82},{"year":2023,"cited_by_count":84},{"year":2022,"cited_by_count":68},{"year":2021,"cited_by_count":66},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2019-03-02T00:00:00"}