{"id":"https://openalex.org/W4379197269","doi":"https://doi.org/10.1186/s12859-023-05350-9","title":"An analysis of entity normalization evaluation biases in specialized domains","display_name":"An analysis of entity normalization evaluation biases in specialized domains","publication_year":2023,"publication_date":"2023-06-02","ids":{"openalex":"https://openalex.org/W4379197269","doi":"https://doi.org/10.1186/s12859-023-05350-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/37268890"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-023-05350-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05350-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05350-9","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05350-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006669344","display_name":"Arnaud Ferr\u00e9","orcid":"https://orcid.org/0000-0001-9115-8222"},"institutions":[{"id":"https://openalex.org/I4210159481","display_name":"Math\u00e9matiques et Informatique Appliqu\u00e9es du G\u00e9nome \u00e0 l'Environnement","ror":"https://ror.org/05qdnns64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210099460","https://openalex.org/I4210159481"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210088668","display_name":"Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement","ror":"https://ror.org/003vg9w96","country_code":"FR","type":"funder","lineage":["https://openalex.org/I4210088668"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Arnaud Ferr\u00e9","raw_affiliation_strings":["MaIAGE, INRAE, Universit\u00e9 Paris-Saclay, Jouy-en-Josas, France. arnaud.ferre@inrae.fr","MaIAGE, INRAE, Universit\u00e9 Paris-Saclay, Jouy-en-Josas, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MaIAGE, INRAE, Universit\u00e9 Paris-Saclay, Jouy-en-Josas, France. arnaud.ferre@inrae.fr","institution_ids":["https://openalex.org/I4210159481","https://openalex.org/I277688954","https://openalex.org/I4210088668"]},{"raw_affiliation_string":"MaIAGE, INRAE, Universit\u00e9 Paris-Saclay, Jouy-en-Josas, France","institution_ids":["https://openalex.org/I4210159481","https://openalex.org/I277688954","https://openalex.org/I4210088668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034154991","display_name":"Philippe Langlais","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Philippe Langlais","raw_affiliation_strings":["RALI, DIRO, Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RALI, DIRO, Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006669344"],"corresponding_institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210088668","https://openalex.org/I4210159481"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.0088,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80441836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"24","issue":"1","first_page":"227","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6288999915122986,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6288999915122986,"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/T11719","display_name":"Data Quality and Management","score":0.16169999539852142,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.04580000042915344,"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/normalization","display_name":"Normalization (sociology)","score":0.9051124453544617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312644124031067},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5531441569328308},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.519645094871521},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5051382184028625},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4347877502441406},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4258610010147095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40548184514045715},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07041728496551514}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9051124453544617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312644124031067},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5531441569328308},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.519645094871521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5051382184028625},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4347877502441406},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4258610010147095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40548184514045715},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07041728496551514},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[{"descriptor_ui":"D001690","descriptor_name":"Biological Science Disciplines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001690","descriptor_name":"Biological Science Disciplines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001690","descriptor_name":"Biological Science Disciplines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001690","descriptor_name":"Biological Science Disciplines","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-023-05350-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05350-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05350-9","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:37268890","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37268890","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:HAL:hal-04115633v1","is_oa":true,"landing_page_url":"https://hal.inrae.fr/hal-04115633","pdf_url":"https://hal.inrae.fr/hal-04115633v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 2023, 24 (1), pp.227. &#x27E8;10.1186/s12859-023-05350-9&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:pubmedcentral.nih.gov:10236701","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10236701","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10236701/pdf/12859_2023_Article_5350.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:ea738e3048574b77863ec901a933ab6d","is_oa":true,"landing_page_url":"https://doaj.org/article/ea738e3048574b77863ec901a933ab6d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 24, Iss 1, Pp 1-29 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-023-05350-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-023-05350-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-023-05350-9","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4379197269.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1550258693","https://openalex.org/W1607035479","https://openalex.org/W1700952868","https://openalex.org/W2034626816","https://openalex.org/W2061166439","https://openalex.org/W2074640468","https://openalex.org/W2122402213","https://openalex.org/W2128049108","https://openalex.org/W2129113459","https://openalex.org/W2131546905","https://openalex.org/W2142016317","https://openalex.org/W2142678031","https://openalex.org/W2143933463","https://openalex.org/W2158743996","https://openalex.org/W2168041406","https://openalex.org/W2169099542","https://openalex.org/W2252174377","https://openalex.org/W2414378847","https://openalex.org/W2415809604","https://openalex.org/W2509884321","https://openalex.org/W2518463060","https://openalex.org/W2763990719","https://openalex.org/W2768645204","https://openalex.org/W2785888191","https://openalex.org/W2808598571","https://openalex.org/W2888236192","https://openalex.org/W2889376139","https://openalex.org/W2892107559","https://openalex.org/W2898256678","https://openalex.org/W2911489562","https://openalex.org/W2914431807","https://openalex.org/W2915128229","https://openalex.org/W2917968119","https://openalex.org/W2921264916","https://openalex.org/W2949845972","https://openalex.org/W2952958555","https://openalex.org/W2964351784","https://openalex.org/W2983315135","https://openalex.org/W2984624504","https://openalex.org/W2985461273","https://openalex.org/W2985754007","https://openalex.org/W3021989992","https://openalex.org/W3029284514","https://openalex.org/W3030645549","https://openalex.org/W3032553678","https://openalex.org/W3034229721","https://openalex.org/W3035021780","https://openalex.org/W3098115739","https://openalex.org/W3103272618","https://openalex.org/W3112302290","https://openalex.org/W3116070535","https://openalex.org/W3116655411","https://openalex.org/W3118356387","https://openalex.org/W3164540570","https://openalex.org/W3168522299","https://openalex.org/W3196318080","https://openalex.org/W3212459720","https://openalex.org/W3212804087","https://openalex.org/W4390849687","https://openalex.org/W4391156274","https://openalex.org/W6600479677"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W2152642030"],"abstract_inverted_index":{"BACKGROUND:":[0],"Entity":[1],"normalization":[2,74],"is":[3,39],"an":[4],"important":[5],"information":[6],"extraction":[7],"task":[8,38],"which":[9],"has":[10],"recently":[11],"gained":[12],"attention,":[13],"particularly":[14],"in":[15,88],"the":[16,37,66,72,85],"clinical/biomedical":[17],"and":[18,51],"life":[19],"science":[20],"domains.":[21],"On":[22],"several":[23],"datasets,":[24],"state-of-the-art":[25,53],"methods":[26,54],"perform":[27],"rather":[28],"well":[29],"on":[30,65],"popular":[31],"benchmarks.":[32],"Yet,":[33],"we":[34],"argue":[35],"that":[36],"far":[40],"from":[41],"resolved.":[42],"RESULTS:":[43],"We":[44,60],"have":[45],"selected":[46],"two":[47,52],"gold":[48],"standard":[49],"corpora":[50],"to":[55,83],"highlight":[56],"some":[57],"evaluation":[58,69,81],"biases.":[59],"present":[61],"non-exhaustive":[62],"initial":[63],"findings":[64],"existence":[67],"of":[68,71],"problems":[70],"entity":[73],"task.":[75],"CONCLUSIONS:":[76],"Our":[77],"analysis":[78],"suggests":[79],"better":[80],"practices":[82],"support":[84],"methodological":[86],"research":[87],"this":[89],"field.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
