{"id":"https://openalex.org/W3208114150","doi":"https://doi.org/10.1080/01639374.2021.1998283","title":"Kratt: Developing an Automatic Subject Indexing Tool for the National Library of Estonia","display_name":"Kratt: Developing an Automatic Subject Indexing Tool for the National Library of Estonia","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W3208114150","doi":"https://doi.org/10.1080/01639374.2021.1998283","mag":"3208114150"},"language":"en","primary_location":{"id":"doi:10.1080/01639374.2021.1998283","doi":"https://doi.org/10.1080/01639374.2021.1998283","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01639374.2021.1998283","pdf_url":null,"source":{"id":"https://openalex.org/S202064188","display_name":"Cataloging & Classification Quarterly","issn_l":"0163-9374","issn":["0163-9374","1544-4554"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","jufo-1","norway-1","poland-70","russia-white-list-3"],"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cataloging &amp; Classification Quarterly","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.12998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071662101","display_name":"Marit Asula","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marit Asula","raw_affiliation_strings":["Texta O\u00dc, Tallinn, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texta O\u00dc, Tallinn, Estonia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002061710","display_name":"Jane Makke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153304","display_name":"National Library of Estonia","ror":"https://ror.org/041d53j42","country_code":"EE","type":"archive","lineage":["https://openalex.org/I4210153304"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Jane Makke","raw_affiliation_strings":["The National Library of Estonia, Library Services Development Centre, Tallinn, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The National Library of Estonia, Library Services Development Centre, Tallinn, Estonia","institution_ids":["https://openalex.org/I4210153304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042665536","display_name":"Linda Freienthal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linda Freienthal","raw_affiliation_strings":["Texta O\u00dc, Tallinn, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texta O\u00dc, Tallinn, Estonia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020956507","display_name":"Hele-Andra Kuulmets","orcid":"https://orcid.org/0009-0000-8068-661X","observed_orcids":["https://orcid.org/0009-0000-8068-661X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hele-Andra Kuulmets","raw_affiliation_strings":["Texta O\u00dc, Tallinn, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texta O\u00dc, Tallinn, Estonia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000204558","display_name":"Raul Sirel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raul Sirel","raw_affiliation_strings":["Texta O\u00dc, Tallinn, Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texta O\u00dc, Tallinn, Estonia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071662101"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9569,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.77757084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"59","issue":"8","first_page":"775","last_page":"793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.9375,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14330","display_name":"Library Science and Information Systems","score":0.9375,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.009399999864399433,"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":0.008999999612569809,"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/automatic-subject-indexing","display_name":"automatic subject indexing","score":0.9890000224113464},{"id":"https://openalex.org/keywords/library-cataloging","display_name":"library cataloging","score":0.6140000224113464},{"id":"https://openalex.org/keywords/training-corpus-size","display_name":"training corpus size","score":0.5419999957084656},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.7829999923706055}],"concepts":[{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.9034045338630676},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8269701600074768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742168664932251},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.7292420864105225},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.6783011555671692},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6773737668991089},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.619333028793335},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5561013221740723},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.523310661315918},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.4909813702106476},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4833492934703827},{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.4350694715976715},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.4178132712841034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929392993450165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3823637366294861},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37513959407806396},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11663550138473511},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1080/01639374.2021.1998283","doi":"https://doi.org/10.1080/01639374.2021.1998283","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01639374.2021.1998283","pdf_url":null,"source":{"id":"https://openalex.org/S202064188","display_name":"Cataloging & Classification Quarterly","issn_l":"0163-9374","issn":["0163-9374","1544-4554"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","jufo-1","norway-1","poland-70","russia-white-list-3"],"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cataloging &amp; Classification Quarterly","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2203.12998","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.12998","pdf_url":"https://arxiv.org/pdf/2203.12998","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:zenodo.org:6434963","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/6434963","pdf_url":"https://zenodo.org/record/6434963","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Cataloging &amp; Classification Quarterly 59(8) 775-793","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2203.12998","doi":"https://doi.org/10.48550/arxiv.2203.12998","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.12998","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.12998","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.12998","pdf_url":"https://arxiv.org/pdf/2203.12998","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5108423257","display_name":"Cross-Lingual Embeddings for Less-Represented Languages in European News Media","funder_award_id":"825153","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8895089711","display_name":"TEXTA Toolkit 2.0","funder_award_id":"EKTR3","funder_id":"https://openalex.org/F4320321976","funder_display_name":"Haridus- ja Teadusministeerium"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321976","display_name":"Haridus- ja Teadusministeerium","ror":"https://ror.org/051aqjh92"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3208114150.pdf","grobid_xml":"https://content.openalex.org/works/W3208114150.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1999639815","https://openalex.org/W2083541257","https://openalex.org/W2116353118","https://openalex.org/W2153594195","https://openalex.org/W2236885731","https://openalex.org/W2964165818","https://openalex.org/W6893752470"],"related_works":["https://openalex.org/W7026881100","https://openalex.org/W4226353670","https://openalex.org/W6997281883","https://openalex.org/W4404482174","https://openalex.org/W7160379617","https://openalex.org/W2964165818","https://openalex.org/W7217743593","https://openalex.org/W4389224485","https://openalex.org/W6893724866","https://openalex.org/W4415592502"],"abstract_inverted_index":{"Manual":[0],"subject":[1,53,60,88],"indexing":[2,54],"in":[3,29,76],"libraries":[4],"is":[5,18,57],"a":[6,48,62,71,90,110,131],"time-consuming":[7],"and":[8,11,68,138],"costly":[9],"process":[10],"the":[12,15,21,25,30,39,77,97,105,107,124,136],"quality":[13],"of":[14,50,65,73,109,113],"assigned":[16],"subjects":[17],"affected":[19],"by":[20,104,129],"cataloger\u2019s":[22],"knowledge":[23],"on":[24],"specific":[26],"topics":[27],"contained":[28],"book.":[31],"Trying":[32],"to":[33,45,59,87],"solve":[34],"these":[35],"issues,":[36],"we":[37],"exploited":[38],"opportunities":[40],"arising":[41],"from":[42],"artificial":[43],"intelligence":[44],"develop":[46],"Kratt:":[47],"prototype":[49],"an":[51],"automatic":[52],"tool.":[55],"Kratt":[56,83],"able":[58],"index":[61,89],"book":[63],"independent":[64],"its":[66],"extent":[67],"genre":[69],"with":[70],"set":[72],"keywords":[74,99],"present":[75],"Estonian":[78],"Subject":[79],"Thesaurus.":[80],"It":[81],"takes":[82],"approximately":[84],"one":[85],"minute":[86],"book,":[91],"outperforming":[92],"humans":[93],"10\u201315":[94],"times.":[95],"Although":[96],"resulting":[98],"were":[100],"not":[101],"considered":[102],"satisfactory":[103],"catalogers,":[106],"ratings":[108],"small":[111],"sample":[112],"regular":[114],"library":[115],"users":[116],"showed":[117],"more":[118,140],"promise.":[119],"We":[120],"also":[121],"argue":[122],"that":[123],"results":[125],"can":[126],"be":[127],"enhanced":[128],"including":[130],"bigger":[132],"corpus":[133],"for":[134],"training":[135],"model":[137],"applying":[139],"careful":[141],"preprocessing":[142],"techniques.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-11-08T00:00:00"}
