{"id":"https://openalex.org/W2924308178","doi":"https://doi.org/10.1007/978-3-030-21348-0_10","title":"Aligning Biomedical Metadata with Ontologies Using Clustering and Embeddings","display_name":"Aligning Biomedical Metadata with Ontologies Using Clustering and Embeddings","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2924308178","doi":"https://doi.org/10.1007/978-3-030-21348-0_10","mag":"2924308178"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-21348-0_10","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-21348-0_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-030-21348-0_10","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049424768","display_name":"Rafael S. Gon\u00e7alves","orcid":"https://orcid.org/0000-0003-1255-0125"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rafael S. Gon\u00e7alves","raw_affiliation_strings":["Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059142933","display_name":"Maulik R. Kamdar","orcid":"https://orcid.org/0000-0002-9898-0515"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maulik R. Kamdar","raw_affiliation_strings":["Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009128820","display_name":"Mark A. Musen","orcid":"https://orcid.org/0000-0003-3325-793X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark A. Musen","raw_affiliation_strings":["Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biomedical Informatics Research, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049424768"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"161"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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/metadata","display_name":"Metadata","score":0.9419771432876587},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.7463277578353882},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7196711301803589},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6646629571914673},{"id":"https://openalex.org/keywords/geospatial-metadata","display_name":"Geospatial metadata","score":0.6290394067764282},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5909373760223389},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5731005668640137},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.5237900018692017},{"id":"https://openalex.org/keywords/open-biomedical-ontologies","display_name":"Open Biomedical Ontologies","score":0.5030290484428406},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.47216862440109253},{"id":"https://openalex.org/keywords/geographic-coordinate-system","display_name":"Geographic coordinate system","score":0.46500739455223083},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.35187309980392456},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.3053286671638489},{"id":"https://openalex.org/keywords/upper-ontology","display_name":"Upper ontology","score":0.2857585549354553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1428503692150116},{"id":"https://openalex.org/keywords/ontology-alignment","display_name":"Ontology alignment","score":0.12030205130577087},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11622539162635803},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.1011146605014801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07927334308624268},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.056311607360839844}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9419771432876587},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7463277578353882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196711301803589},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6646629571914673},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.6290394067764282},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5909373760223389},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5731005668640137},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.5237900018692017},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.5030290484428406},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.47216862440109253},{"id":"https://openalex.org/C123046963","wikidata":"https://www.wikidata.org/wiki/Q22664","display_name":"Geographic coordinate system","level":2,"score":0.46500739455223083},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.35187309980392456},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.3053286671638489},{"id":"https://openalex.org/C78726541","wikidata":"https://www.wikidata.org/wiki/Q3882785","display_name":"Upper ontology","level":3,"score":0.2857585549354553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1428503692150116},{"id":"https://openalex.org/C98893333","wikidata":"https://www.wikidata.org/wiki/Q4339878","display_name":"Ontology alignment","level":4,"score":0.12030205130577087},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11622539162635803},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.1011146605014801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07927334308624268},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.056311607360839844},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-21348-0_10","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-21348-0_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:1903.08206","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08206","pdf_url":"https://arxiv.org/pdf/1903.08206","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:10.1007/978-3-030-21348-0_10","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-21348-0_10","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W423733794","https://openalex.org/W1673310716","https://openalex.org/W2015747862","https://openalex.org/W2036288429","https://openalex.org/W2106797966","https://openalex.org/W2118100588","https://openalex.org/W2127426251","https://openalex.org/W2131571251","https://openalex.org/W2131660156","https://openalex.org/W2165232124","https://openalex.org/W2184957013","https://openalex.org/W2250539671","https://openalex.org/W2283196293","https://openalex.org/W2302501749","https://openalex.org/W2523679382","https://openalex.org/W2601243251","https://openalex.org/W2766208765","https://openalex.org/W2773787581","https://openalex.org/W2787438497","https://openalex.org/W2950750198","https://openalex.org/W2962969117","https://openalex.org/W2963923670","https://openalex.org/W2964266863","https://openalex.org/W3100689701","https://openalex.org/W4400177176"],"related_works":["https://openalex.org/W2374379029","https://openalex.org/W1503116306","https://openalex.org/W2373398412","https://openalex.org/W2360250168","https://openalex.org/W3016521766","https://openalex.org/W2018424284","https://openalex.org/W3084772717","https://openalex.org/W132275995","https://openalex.org/W2008531296","https://openalex.org/W2354596657"],"abstract_inverted_index":{"The":[0],"metadata":[1,47,73,84,118,130,168],"about":[2],"scientific":[3,51],"experiments":[4],"published":[5],"in":[6,60,83,136],"online":[7],"repositories":[8],"have":[9,48],"been":[10],"shown":[11],"to":[12,25,75,91,116,128],"suffer":[13],"from":[14,139],"a":[15,34,61,103,146],"high":[16],"degree":[17],"of":[18,30,96,114],"representational":[19],"heterogeneity\u2014there":[20],"are":[21],"often":[22],"many":[23],"ways":[24],"represent":[26],"the":[27,44,77,93,140,153],"same":[28,94],"type":[29,95],"information,":[31],"such":[32],"as":[33],"geographical":[35],"location":[36],"via":[37],"its":[38],"latitude":[39],"and":[40,89,109,152,163,169],"longitude.":[41],"To":[42,98],"harness":[43],"potential":[45],"that":[46,56,64,99,158],"for":[49,134],"discovering":[50],"data,":[52],"it":[53],"is":[54,74],"crucial":[55],"they":[57],"be":[58,66],"represented":[59],"uniform":[62],"way":[63],"can":[65],"queried":[67],"effectively.":[68],"One":[69],"step":[70],"toward":[71],"uniformly-represented":[72],"normalize":[76],"multiple,":[78],"distinct":[79],"field":[80,119],"names":[81,120],"used":[82],"(e.g.,":[85],"lat":[86,88],"lon,":[87],"long)":[90],"describe":[92],"value.":[97],"end,":[100],"we":[101],"present":[102],"new":[104],"method":[105,127,151,160],"based":[106],"on":[107],"clustering":[108],"embeddings":[110,133],"(i.e.,":[111],"vector":[112],"representations":[113],"words)":[115],"align":[117],"with":[121],"ontology":[122,170],"terms.":[123,171],"We":[124,143],"apply":[125],"our":[126,150,159],"biomedical":[129,137],"by":[131],"generating":[132],"terms":[135],"ontologies":[138],"BioPortal":[141],"repository.":[142],"carried":[144],"out":[145],"comparative":[147],"study":[148],"between":[149,167],"NCBO":[154],"Annotator,":[155],"which":[156],"revealed":[157],"yields":[161],"more":[162],"substantially":[164],"better":[165],"alignments":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-04-01T00:00:00"}
