{"id":"https://openalex.org/W4410356995","doi":"https://doi.org/10.1145/3672608.3707906","title":"Taxonomy Expansion through Collaborative LLM Mapping","display_name":"Taxonomy Expansion through Collaborative LLM Mapping","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410356995","doi":"https://doi.org/10.1145/3672608.3707906"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707906","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707906","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707906","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102781905","display_name":"Simone D\u2019Amico","orcid":"https://orcid.org/0009-0002-2820-0277"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Simone D'Amico","raw_affiliation_strings":["University of Milano-Bicocca, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056749454","display_name":"Alessia De Santo","orcid":null},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessia De Santo","raw_affiliation_strings":["University of Milan Bicocca, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"University of Milan Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039716498","display_name":"Mario Mezzanzanica","orcid":"https://orcid.org/0000-0003-0399-2810"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Mezzanzanica","raw_affiliation_strings":["Department of Statistics, Universit\u00e0 degli Studi di Milano Bicocca, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Universit\u00e0 degli Studi di Milano Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047827615","display_name":"Fabio Mercorio","orcid":"https://orcid.org/0000-0001-6864-2702"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Mercorio","raw_affiliation_strings":["University of Milano Bicocca, Milano, Italy"],"affiliations":[{"raw_affiliation_string":"University of Milano Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102781905"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":3.4116,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91576512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1961","last_page":"1968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9965999722480774,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9965999722480774,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9958000183105469,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9876999855041504,"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/computer-science","display_name":"Computer science","score":0.6343435645103455},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5499770045280457},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.09881576895713806},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0969247817993164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6343435645103455},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5499770045280457},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.09881576895713806},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0969247817993164}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3672608.3707906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707906","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707906","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/555061","is_oa":false,"landing_page_url":"https://hdl.handle.net/10281/555061","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3672608.3707906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707906","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707906","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410356995.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2798965707","https://openalex.org/W2883153670","https://openalex.org/W2962992134","https://openalex.org/W3012615229","https://openalex.org/W3012823870","https://openalex.org/W3036413095","https://openalex.org/W3096130309","https://openalex.org/W3103941499","https://openalex.org/W3114918172","https://openalex.org/W3200327212","https://openalex.org/W3212837704","https://openalex.org/W4211076749","https://openalex.org/W4221153270","https://openalex.org/W4297035741","https://openalex.org/W4312833999","https://openalex.org/W4320523283"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Hierarchical":[0],"taxonomies":[1,43],"are":[2],"crucial":[3],"for":[4],"organizing":[5],"concepts":[6],"across":[7],"domains":[8],"like":[9],"healthcare,":[10],"finance,":[11],"and":[12,48,119],"economics.":[13],"However,":[14],"maintaining":[15],"their":[16],"accuracy":[17],"requires":[18],"continuous":[19],"updates,":[20],"often":[21],"demanding":[22],"expert":[23],"input.":[24],"To":[25],"address":[26],"this,":[27],"we":[28],"propose":[29],"TAXMAP":[30,113],"(TAxonomy":[31],"eXpansion":[32],"through":[33],"Collaborative":[34],"LLM":[35],"MAPping),":[36],"a":[37,53,125],"system":[38,132],"that":[39],"autonomously":[40],"expands":[41],"hierarchical":[42],"using":[44],"contextual":[45],"word":[46],"embeddings":[47],"three":[49,143],"generative":[50],"models,":[51],"with":[52,85],"human":[54,121],"validation":[55],"step":[56],"ensuring":[57],"relevance.":[58],"Implemented":[59],"within":[60],"an":[61,134],"EU":[62],"initiative":[63],"to":[64,124],"enhance":[65],"the":[66,80],"European":[67],"Skill":[68],"taxonomy":[69],"(ESCO),":[70],"our":[71,131],"framework":[72],"processed":[73],"over":[74],"40,000":[75],"digital":[76],"terms":[77],"gathered":[78],"from":[79],"Web,":[81],"aligning":[82],"ESCO":[83],"skills":[84],"labor":[86],"market":[87],"needs.":[88],"This":[89],"effort":[90],"resulted":[91],"in":[92],"924":[93],"proposed":[94],"terms,":[95],"757":[96],"of":[97],"which":[98],"were":[99],"validated":[100],"by":[101],"experts":[102],"as":[103,111],"correct.":[104],"By":[105],"leveraging":[106],"large":[107],"language":[108],"models":[109],"(LLMs)":[110],"encoders,":[112],"reduces":[114],"errors,":[115],"ensures":[116],"high":[117],"precision,":[118],"minimizes":[120],"effort.":[122],"Compared":[123],"baseline":[126],"based":[127],"on":[128],"ESCO's":[129],"hierarchy,":[130],"achieved":[133],"81%":[135],"Positive":[136],"Predictive":[137],"Value":[138],"(PPV)":[139],"when":[140],"combining":[141],"all":[142],"models.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}
