{"id":"https://openalex.org/W2515582862","doi":"https://doi.org/10.18653/v1/w16-2913","title":"Syntactic analyses and named entity recognition for PubMed and PubMed Central \u2014 up-to-the-minute","display_name":"Syntactic analyses and named entity recognition for PubMed and PubMed Central \u2014 up-to-the-minute","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2515582862","doi":"https://doi.org/10.18653/v1/w16-2913","mag":"2515582862"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2913","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2913","pdf_url":"https://aclanthology.org/W16-2913.pdf","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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W16-2913.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058939594","display_name":"Kai Hakala","orcid":"https://orcid.org/0000-0001-8943-7011"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kai Hakala","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000080545","display_name":"Suwisa Kaewphan","orcid":"https://orcid.org/0000-0001-8534-1215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suwisa Kaewphan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105839982","display_name":"Tapio Salakoski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tapio Salakoski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019929457","display_name":"Filip Ginter","orcid":"https://orcid.org/0000-0002-5484-6103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Filip Ginter","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058939594"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0919,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87318183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9954000115394592,"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":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.8589397668838501},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.684181809425354},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5813785195350647},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5671868920326233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5569794774055481},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.5340614914894104},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.5148481726646423},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4936729371547699},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4881592392921448},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47350507974624634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4451413154602051},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.425975501537323},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3825441598892212},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.23298603296279907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8589397668838501},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.684181809425354},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5813785195350647},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5671868920326233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5569794774055481},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5340614914894104},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.5148481726646423},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4936729371547699},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4881592392921448},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47350507974624634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4451413154602051},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.425975501537323},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3825441598892212},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.23298603296279907},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w16-2913","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2913","pdf_url":"https://aclanthology.org/W16-2913.pdf","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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2913","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2913","pdf_url":"https://aclanthology.org/W16-2913.pdf","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 15th Workshop on Biomedical Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2515582862.pdf","grobid_xml":"https://content.openalex.org/works/W2515582862.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W122290181","https://openalex.org/W1508977358","https://openalex.org/W2032566933","https://openalex.org/W2035807240","https://openalex.org/W2048140075","https://openalex.org/W2051547811","https://openalex.org/W2053673723","https://openalex.org/W2065963191","https://openalex.org/W2100276951","https://openalex.org/W2105924489","https://openalex.org/W2107005506","https://openalex.org/W2120754707","https://openalex.org/W2131284830","https://openalex.org/W2142016317","https://openalex.org/W2148488766","https://openalex.org/W2149369282","https://openalex.org/W2169099542","https://openalex.org/W2169491861","https://openalex.org/W2171374484","https://openalex.org/W2229453122","https://openalex.org/W2251279337"],"related_works":["https://openalex.org/W2134429551","https://openalex.org/W3004288456","https://openalex.org/W4292346028","https://openalex.org/W2548624545","https://openalex.org/W2725310424","https://openalex.org/W4282591925","https://openalex.org/W2891935779","https://openalex.org/W2963023579","https://openalex.org/W2766198569","https://openalex.org/W2017675085"],"abstract_inverted_index":{"Although":[0],"advanced":[1],"text":[2,41,79],"mining":[3,80],"methods":[4],"specifically":[5],"adapted":[6],"to":[7,72],"the":[8,24,30,74,84,93,126],"biomedical":[9,53],"domain":[10],"are":[11],"continuously":[12],"being":[13],"developed,":[14],"their":[15],"applications":[16],"on":[17,119],"large":[18,40],"scale":[19],"have":[20],"been":[21],"scarce.One":[22],"of":[23,32,68,77,95],"main":[25],"reasons":[26],"for":[27,38],"this":[28,43,69],"is":[29,71,117,129,133],"lack":[31],"computational":[33],"resources":[34,81],"and":[35,63,97,107],"workforce":[36],"required":[37],"processing":[39],"corpora.In":[42],"paper":[44],"we":[45],"present":[46],"a":[47,120],"publicly":[48],"available":[49,134],"resource":[50,91,116,132],"distributing":[51],"preprocessed":[52],"literature":[54],"including":[55],"sentence":[56],"splitting,":[57],"tokenization,":[58],"part-of-speech":[59],"tagging,":[60],"syntactic":[61],"parses":[62],"named":[64],"entity":[65],"recognition.The":[66],"aim":[67],"work":[70],"support":[73],"future":[75],"development":[76],"largescale":[78],"by":[82],"eliminating":[83],"time":[85],"consuming":[86],"but":[87],"necessary":[88],"preprocessing":[89],"steps.This":[90],"covers":[92],"whole":[94],"PubMed":[96,98],"Central":[99],"Open":[100],"Access":[101],"section,":[102],"currently":[103],"containing":[104],"26M":[105],"abstracts":[106],"1.4M":[108],"full":[109],"articles,":[110],"constituting":[111],"over":[112],"388M":[113],"analyzed":[114],"sentences.The":[115],"based":[118],"fully":[121],"automated":[122],"pipeline,":[123],"guaranteeing":[124],"that":[125],"distributed":[127],"data":[128],"always":[130],"up-to-date.The":[131],"at":[135],"https://turkunlp.github.io/pubmed_parses/.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}