{"id":"https://openalex.org/W4415504759","doi":"https://doi.org/10.3366/ijhac.2025.0353","title":"Cost-Effective Machine Learning for Automatically Processing Bibliographic Metadata","display_name":"Cost-Effective Machine Learning for Automatically Processing Bibliographic Metadata","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4415504759","doi":"https://doi.org/10.3366/ijhac.2025.0353"},"language":"en","primary_location":{"id":"doi:10.3366/ijhac.2025.0353","is_oa":false,"landing_page_url":"https://doi.org/10.3366/ijhac.2025.0353","pdf_url":null,"source":{"id":"https://openalex.org/S123953891","display_name":"International Journal of Humanities and Arts Computing","issn_l":"1753-8548","issn":["1753-8548","1755-1706"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320189","host_organization_name":"Edinburgh University Press","host_organization_lineage":["https://openalex.org/P4310320189"],"host_organization_lineage_names":["Edinburgh University Press"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanities and Arts Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034452468","display_name":"Samuel J. Huskey","orcid":"https://orcid.org/0000-0002-8192-9385"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel J. Huskey","raw_affiliation_strings":["University of Oklahoma"],"raw_orcid":"https://orcid.org/0000-0002-8192-9385","affiliations":[{"raw_affiliation_string":"University of Oklahoma","institution_ids":["https://openalex.org/I8692664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5034452468"],"corresponding_institution_ids":["https://openalex.org/I8692664"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34307332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"2","first_page":"112","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9661999940872192,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9661999940872192,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9395999908447266,"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":0.7286999821662903},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5896999835968018},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.566100001335144},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5231999754905701}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026999831199646},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7286999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954999923706055},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.566100001335144},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5231999754905701},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47369998693466187},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2865999937057495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3366/ijhac.2025.0353","is_oa":false,"landing_page_url":"https://doi.org/10.3366/ijhac.2025.0353","pdf_url":null,"source":{"id":"https://openalex.org/S123953891","display_name":"International Journal of Humanities and Arts Computing","issn_l":"1753-8548","issn":["1753-8548","1755-1706"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320189","host_organization_name":"Edinburgh University Press","host_organization_lineage":["https://openalex.org/P4310320189"],"host_organization_lineage_names":["Edinburgh University Press"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Humanities and Arts Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Many":[0],"digital":[1],"humanities":[2],"projects":[3],"involve":[4],"tedious":[5,29,114],"and":[6,30,64,68],"repetitive":[7,31],"tasks":[8,15,32,45],"that":[9,20,50,61,106,117],"take":[10],"time":[11],"away":[12],"from":[13],"higher-level":[14],"further":[16],"down":[17],"the":[18,107,118,127,132,138,141,146],"pipeline":[19],"require":[21],"intelligent":[22],"decision":[23],"making.":[24],"When":[25],"funding":[26,41],"is":[27,42],"available,":[28],"are":[33,70],"often":[34],"assigned":[35],"to":[36,47,77,98,136],"research":[37],"assistants,":[38],"but":[39,116],"when":[40],"scarce,":[43],"those":[44],"tend":[46],"create":[48],"bottlenecks":[49],"either":[51],"impede":[52],"progress":[53],"or":[54],"halt":[55],"it":[56],"altogether.":[57],"This":[58],"article":[59],"argues":[60],"artificial":[62],"intelligence":[63],"machine":[65],"learning":[66],"tools":[67],"techniques":[69],"worth":[71],"exploring":[72],"as":[73],"cost-effective,":[74],"accessible":[75],"solutions":[76],"these":[78],"problems.":[79],"The":[80,103],"Digital":[81],"Latin":[82],"Library":[83],"project":[84],"provides":[85],"a":[86],"case":[87],"study":[88],"through":[89],"its":[90],"experiments":[91,119],"with":[92],"fine-tuning":[93],"pretrained":[94],"transformer":[95],"language":[96],"models":[97,108,128],"process":[99],"noisy":[100],"bibliographic":[101],"metadata.":[102],"results":[104],"show":[105],"have":[109],"potential":[110],"for":[111],"accelerating":[112],"this":[113],"task,":[115],"also":[120],"had":[121],"an":[122],"unexpected,":[123],"if":[124],"positive,":[125],"outcome:":[126],"revealed":[129],"gaps":[130],"in":[131],"catalogue\u2019s":[133],"coverage,":[134],"helping":[135],"focus":[137],"efforts":[139],"of":[140],"human":[142],"experts":[143],"working":[144],"on":[145],"project.":[147]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-24T00:00:00"}