{"id":"https://openalex.org/W4385291862","doi":"https://doi.org/10.4126/frl01-006444995","title":"Making Metadata More FAIR Using Large Language Models","display_name":"Making Metadata More FAIR Using Large Language Models","publication_year":2023,"publication_date":"2023-04-28","ids":{"openalex":"https://openalex.org/W4385291862","doi":"https://doi.org/10.4126/frl01-006444995"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.13085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.13085","pdf_url":"https://arxiv.org/pdf/2307.13085","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.13085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006341541","display_name":"Sowmya S. Sundaram","orcid":"https://orcid.org/0000-0002-0086-7582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundaram, Sowmya S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009128820","display_name":"Mark A. Musen","orcid":"https://orcid.org/0000-0003-3325-793X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Musen, Mark A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.988099992275238,"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":0.988099992275238,"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":0.9599000215530396,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9571999907493591,"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":0.968727707862854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.786659836769104},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6514964699745178},{"id":"https://openalex.org/keywords/metadata-modeling","display_name":"Metadata modeling","score":0.5374557971954346},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5188880562782288},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4932946562767029},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4858652949333191},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4829408526420593},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4774359166622162},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.4700091481208801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4668009877204895},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.43846818804740906},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4362068772315979},{"id":"https://openalex.org/keywords/geospatial-metadata","display_name":"Geospatial metadata","score":0.4104897081851959},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3772231638431549},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.37391626834869385},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27890729904174805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24623161554336548},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23724791407585144},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.09482565522193909}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.968727707862854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786659836769104},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6514964699745178},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.5374557971954346},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5188880562782288},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4932946562767029},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4858652949333191},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4829408526420593},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4774359166622162},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.4700091481208801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4668009877204895},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.43846818804740906},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4362068772315979},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.4104897081851959},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3772231638431549},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.37391626834869385},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27890729904174805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24623161554336548},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23724791407585144},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.09482565522193909},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2307.13085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.13085","pdf_url":"https://arxiv.org/pdf/2307.13085","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.13085","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.13085","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.4126/frl01-006444995","is_oa":true,"landing_page_url":"https://doi.org/10.4126/frl01-006444995","pdf_url":null,"source":{"id":"https://openalex.org/S7407053505","display_name":"Fachrepositorium Lebenswissenschaften","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.13085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.13085","pdf_url":"https://arxiv.org/pdf/2307.13085","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7915982384","display_name":null,"funder_award_id":"R01 LM013498","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"},{"id":"https://openalex.org/F4320338403","display_name":"Common Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385291862.pdf","grobid_xml":"https://content.openalex.org/works/W4385291862.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2374379029","https://openalex.org/W3084772717","https://openalex.org/W2373398412","https://openalex.org/W2018424284","https://openalex.org/W2367786714","https://openalex.org/W132275995","https://openalex.org/W2907247951","https://openalex.org/W2360250168","https://openalex.org/W92613187","https://openalex.org/W2366289621"],"abstract_inverted_index":{"With":[0],"the":[1,45,87,125,141],"global":[2],"increase":[3],"in":[4,10,128],"experimental":[5,138],"data":[6],"artifacts,":[7],"harnessing":[8],"them":[9],"a":[11,16,30,53,112],"unified":[12],"fashion":[13],"leads":[14],"to":[15],"major":[17],"stumbling":[18],"block":[19],"-":[20],"bad":[21],"metadata.":[22,41],"To":[23],"bridge":[24],"this":[25,27],"gap,":[26],"work":[28],"presents":[29],"Natural":[31],"Language":[32,117],"Processing":[33],"(NLP)":[34],"informed":[35],"application,":[36],"called":[37],"FAIRMetaText,":[38],"that":[39],"compares":[40],"Specifically,":[42],"FAIRMetaText":[43],"analyzes":[44],"natural":[46,132],"language":[47,133],"descriptions":[48],"of":[49,81,86,111,115],"metadata":[50,104,134],"and":[51,92,99],"provides":[52],"mathematical":[54],"similarity":[55],"measure":[56,61],"between":[57],"two":[58],"terms.":[59,83],"This":[60,120],"can":[62,122],"then":[63],"be":[64],"utilized":[65],"for":[66,73,79],"analyzing":[67],"varied":[68],"metadata,":[69],"by":[70],"suggesting":[71],"terms":[72,78],"compliance":[74],"or":[75],"grouping":[76],"similar":[77],"identification":[80],"replaceable":[82],"The":[84],"efficacy":[85],"algorithm":[88],"is":[89],"presented":[90],"qualitatively":[91],"quantitatively":[93],"on":[94,140],"publicly":[95],"available":[96],"research":[97],"artifacts":[98],"demonstrates":[100],"large":[101],"gains":[102],"across":[103],"related":[105],"tasks":[106],"through":[107,130],"an":[108],"in-depth":[109],"study":[110],"wide":[113],"variety":[114],"Large":[116],"Models":[118],"(LLMs).":[119],"software":[121],"drastically":[123],"reduce":[124],"human":[126],"effort":[127],"sifting":[129],"various":[131],"while":[135],"employing":[136],"several":[137],"datasets":[139],"same":[142],"topic.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2023-07-27T00:00:00"}