{"id":"https://openalex.org/W4416902886","doi":"https://doi.org/10.48550/arxiv.2504.19675","title":"Annif at SemEval-2025 Task 5: Traditional XMTC augmented by LLMs","display_name":"Annif at SemEval-2025 Task 5: Traditional XMTC augmented by LLMs","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4416902886","doi":"https://doi.org/10.48550/arxiv.2504.19675"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.19675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.19675","pdf_url":"https://arxiv.org/pdf/2504.19675","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":"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.19675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014308772","display_name":"Osma Suominen","orcid":"https://orcid.org/0000-0003-0042-0745","observed_orcids":["https://orcid.org/0000-0003-0042-0745"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I4391767722","display_name":"National Library of Finland","ror":"https://ror.org/03qr6jw57","country_code":"FI","type":"archive","lineage":["https://openalex.org/I133731052","https://openalex.org/I4391767722"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Suominen, Osma","raw_affiliation_strings":["National Library of Finland , University of Helsinki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Finland , University of Helsinki","institution_ids":["https://openalex.org/I133731052","https://openalex.org/I4391767722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085498804","display_name":"Juho Inkinen","orcid":"https://orcid.org/0000-0002-6497-6171","observed_orcids":["https://orcid.org/0000-0002-6497-6171"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I4391767722","display_name":"National Library of Finland","ror":"https://ror.org/03qr6jw57","country_code":"FI","type":"archive","lineage":["https://openalex.org/I133731052","https://openalex.org/I4391767722"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Inkinen, Juho","raw_affiliation_strings":["National Library of Finland , University of Helsinki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Finland , University of Helsinki","institution_ids":["https://openalex.org/I133731052","https://openalex.org/I4391767722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036734716","display_name":"Mona Lehtinen","orcid":"https://orcid.org/0000-0002-4735-0214","observed_orcids":["https://orcid.org/0000-0002-4735-0214"]},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I4391767722","display_name":"National Library of Finland","ror":"https://ror.org/03qr6jw57","country_code":"FI","type":"archive","lineage":["https://openalex.org/I133731052","https://openalex.org/I4391767722"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lehtinen, Mona","raw_affiliation_strings":["National Library of Finland , University of Helsinki"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Finland , University of Helsinki","institution_ids":["https://openalex.org/I133731052","https://openalex.org/I4391767722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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":0.5195000171661377,"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":0.5195000171661377,"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/T14330","display_name":"Library Science and Information Systems","score":0.3361999988555908,"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":0.053300000727176666,"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/subject-indexing","display_name":"subject indexing","score":0.9300000071525574},{"id":"https://openalex.org/keywords/annif","display_name":"Annif","score":0.6790000200271606},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7730000019073486},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.9160000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829999923706055},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7626000046730042},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7253999710083008},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.7164000272750854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6381999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322000026702881},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4641999900341034},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2778756484","wikidata":"https://www.wikidata.org/wiki/Q7631388","display_name":"Subject access","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2504.19675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.19675","pdf_url":"https://arxiv.org/pdf/2504.19675","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":"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":"pmh:oai:helda.helsinki.fi:10138/628953","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/628953","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"doi:10.48550/arxiv.2504.19675","doi":"https://doi.org/10.48550/arxiv.2504.19675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.19675","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.19675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.19675","pdf_url":"https://arxiv.org/pdf/2504.19675","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":"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310086","display_name":"Helsingin Yliopisto","ror":"https://ror.org/040af2s02"},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416902886.pdf","grobid_xml":"https://content.openalex.org/works/W4416902886.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3093858897","https://openalex.org/W4401306886"],"related_works":["https://openalex.org/W4417058215","https://openalex.org/W4417523722","https://openalex.org/W6930623600","https://openalex.org/W7220786171","https://openalex.org/W7092207799","https://openalex.org/W4415248912","https://openalex.org/W7169599298","https://openalex.org/W7202114391","https://openalex.org/W4416284967","https://openalex.org/W7112733062"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,31,36,53,77,83,87,98,111],"Annif":[4,54],"system":[5,73],"in":[6,52,76,82,86,92,118],"SemEval-2025":[7],"Task":[8],"5":[9],"(LLMs4Subjects),":[10],"which":[11],"focussed":[12],"on":[13],"subject":[14,25,38,116],"indexing":[15,117],"using":[16,35],"large":[17],"language":[18,45],"models":[19],"(LLMs).":[20],"The":[21,72],"task":[22],"required":[23],"creating":[24],"predictions":[26,68],"for":[27,60],"bibliographic":[28],"records":[29],"from":[30,69],"bilingual":[32],"TIBKAT":[33],"database":[34],"GND":[37],"vocabulary.":[39],"Our":[40],"approach":[41],"combines":[42],"traditional":[43,102],"natural":[44],"processing":[46],"and":[47,62,66,80,90,113],"machine":[48],"learning":[49],"techniques":[50,108],"implemented":[51],"toolkit":[55],"with":[56,105],"innovative":[57],"LLM-based":[58],"methods":[59],"translation":[61],"synthetic":[63],"data":[64],"generation,":[65],"merging":[67],"monolingual":[70],"models.":[71],"ranked":[74],"first":[75],"all-subjects":[78],"category":[79,85],"second":[81],"tib-core-subjects":[84],"quantitative":[88],"evaluation,":[89],"fourth":[91],"qualitative":[93],"evaluations.":[94],"These":[95],"findings":[96],"demonstrate":[97],"potential":[99],"of":[100,115],"combining":[101],"XMTC":[103],"algorithms":[104],"modern":[106],"LLM":[107],"to":[109],"improve":[110],"accuracy":[112],"efficiency":[114],"multilingual":[119],"contexts.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
