{"id":"https://openalex.org/W2251937554","doi":"https://doi.org/10.18653/v1/w15-2605","title":"An Analysis of Biomedical Tokenization: Problems and Strategies","display_name":"An Analysis of Biomedical Tokenization: Problems and Strategies","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2251937554","doi":"https://doi.org/10.18653/v1/w15-2605","mag":"2251937554"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-2605","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2605","pdf_url":"https://aclanthology.org/W15-2605.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 Sixth International Workshop on Health Text Mining and Information Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W15-2605.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020931358","display_name":"Noa P. Cruz D\u00edaz","orcid":null},"institutions":[{"id":"https://openalex.org/I78880903","display_name":"Universidad de Huelva","ror":"https://ror.org/03a1kt624","country_code":"ES","type":"education","lineage":["https://openalex.org/I78880903"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Noa P. Cruz Diaz","raw_affiliation_strings":["University of Huelva, Huelva, Spain"],"affiliations":[{"raw_affiliation_string":"University of Huelva, Huelva, Spain","institution_ids":["https://openalex.org/I78880903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104067775","display_name":"Manuel Ma\u00f1a L\u00f3pez","orcid":null},"institutions":[{"id":"https://openalex.org/I78880903","display_name":"Universidad de Huelva","ror":"https://ror.org/03a1kt624","country_code":"ES","type":"education","lineage":["https://openalex.org/I78880903"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Manuel Ma\u00f1a L\u00f3pez","raw_affiliation_strings":["University of Huelva, Huelva, Spain"],"affiliations":[{"raw_affiliation_string":"University of Huelva, Huelva, Spain","institution_ids":["https://openalex.org/I78880903"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104067775"],"corresponding_institution_ids":["https://openalex.org/I78880903"],"apc_list":null,"apc_paid":null,"fwci":0.3019,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.63206884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9847999811172485,"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":0.9847999811172485,"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":0.9674000144004822,"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":0.9412000179290771,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9418225288391113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8268473744392395},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7315802574157715},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.6508806347846985},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6398665904998779},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6127730011940002},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.610241174697876},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.553157389163971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37257295846939087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36065882444381714},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33918821811676025},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.320068895816803},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2107948660850525},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08954378962516785}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9418225288391113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268473744392395},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7315802574157715},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6508806347846985},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6398665904998779},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6127730011940002},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.610241174697876},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.553157389163971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37257295846939087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36065882444381714},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33918821811676025},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.320068895816803},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2107948660850525},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08954378962516785},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w15-2605","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2605","pdf_url":"https://aclanthology.org/W15-2605.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 Sixth International Workshop on Health Text Mining and Information Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:rabida.uhu.es:10272/11951","is_oa":true,"landing_page_url":"http://hdl.handle.net/10272/11951","pdf_url":null,"source":{"id":"https://openalex.org/S4306401308","display_name":"Repositorio Institucional de la Universidad de Huelva (Universidad de Huelva)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78880903","host_organization_name":"Universidad de Huelva","host_organization_lineage":["https://openalex.org/I78880903"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference output"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-2605","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-2605","pdf_url":"https://aclanthology.org/W15-2605.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 Sixth International Workshop on Health Text Mining and Information Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251937554.pdf","grobid_xml":"https://content.openalex.org/works/W2251937554.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W24718583","https://openalex.org/W66137051","https://openalex.org/W122290181","https://openalex.org/W123309796","https://openalex.org/W182831726","https://openalex.org/W192665053","https://openalex.org/W1237926134","https://openalex.org/W1482328859","https://openalex.org/W1483313504","https://openalex.org/W1521626219","https://openalex.org/W1538486977","https://openalex.org/W1592053870","https://openalex.org/W1907024343","https://openalex.org/W1973406306","https://openalex.org/W1982464493","https://openalex.org/W2032021697","https://openalex.org/W2034137005","https://openalex.org/W2037450062","https://openalex.org/W2039612385","https://openalex.org/W2048140075","https://openalex.org/W2049029822","https://openalex.org/W2049810512","https://openalex.org/W2055032581","https://openalex.org/W2116159459","https://openalex.org/W2127147316","https://openalex.org/W2127241285","https://openalex.org/W2151296343","https://openalex.org/W2158789585","https://openalex.org/W2169818249","https://openalex.org/W2426119782","https://openalex.org/W2501397611","https://openalex.org/W2586232578","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4366851046","https://openalex.org/W3172681236","https://openalex.org/W2033371749","https://openalex.org/W3214032513","https://openalex.org/W4380568733"],"abstract_inverted_index":{"Choosing":[0],"the":[1,10,23,44,62,68,73,89,119],"right":[2,69],"tokenizer":[3],"is":[4],"a":[5,47],"non-trivial":[6],"task,":[7],"especially":[8],"in":[9,27,116],"biomedical":[11,101],"domain,":[12],"where":[13],"it":[14,78],"poses":[15],"additional":[16],"challenges,":[17],"which":[18],"if":[19],"not":[20],"resolved":[21],"means":[22],"propagation":[24],"of":[25,53,66,94,105,109,121],"errors":[26],"successive":[28],"Natural":[29],"Language":[30],"Processing":[31],"analysis":[32],"pipeline.":[33],"This":[34,58],"paper":[35],"aims":[36],"to":[37,72,82,118],"identify":[38],"these":[39],"problematic":[40,96],"cases":[41,97],"and":[42,49,114],"analyze":[43],"output":[45],"that,":[46],"representative":[48],"widely":[50],"used":[51],"set":[52],"tokenizers,":[54],"shows":[55],"on":[56],"them.":[57,106],"work":[59],"will":[60,79],"aid":[61],"decision":[63],"making":[64],"process":[65],"choosing":[67],"strategy":[70],"according":[71],"downstream":[74],"application.":[75],"In":[76],"addition,":[77],"help":[80],"developers":[81],"create":[83],"accurate":[84],"tokenization":[85],"tools":[86],"or":[87],"improve":[88],"existing":[90],"ones.":[91],"A":[92],"total":[93],"14":[95],"were":[98,112],"described,":[99],"showing":[100],"samples":[102],"for":[103],"each":[104],"The":[107],"outputs":[108],"12":[110],"tokenizers":[111],"provided":[113],"discussed":[115],"relation":[117],"level":[120],"agreement":[122],"among":[123],"tools.":[124]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}
