{"id":"https://openalex.org/W4416037187","doi":"https://doi.org/10.18653/v1/2025.emnlp-industry.113","title":"Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration","display_name":"Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037187","doi":"https://doi.org/10.18653/v1/2025.emnlp-industry.113"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.emnlp-industry.113","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100341082","display_name":"Nan Li","orcid":"https://orcid.org/0000-0002-8248-9027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110764212","display_name":"Bo Ram Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076045275","display_name":"Tijl De Bie","orcid":"https://orcid.org/0000-0002-2692-7504"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tijl De Bie","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1596","last_page":"1614"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.13179999589920044,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.13179999589920044,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.04809999838471413,"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/T10028","display_name":"Topic Modeling","score":0.046799998730421066,"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/scalability","display_name":"Scalability","score":0.6212999820709229},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5885000228881836},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/climb","display_name":"Climb","score":0.5019999742507935},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.39239999651908875},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.3912999927997589},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379999756813049},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2778168010","wikidata":"https://www.wikidata.org/wiki/Q1499786","display_name":"Climb","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38499999046325684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3416999876499176},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C2778180026","wikidata":"https://www.wikidata.org/wiki/Q18378163","display_name":"Semantic heterogeneity","level":4,"score":0.3009999990463257},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-industry.113","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-industry.113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01KAB1JM742RT2SR48YDS3DPYJ","is_oa":false,"landing_page_url":"http://hdl.handle.net/1854/LU-01KAB1JM742RT2SR48YDS3DPYJ","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798891763333","raw_type":"info:eu-repo/semantics/conferenceObject"}],"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":{"Creating":[0],"robust":[1],"occupation":[2],"taxonomies,":[3],"vital":[4],"for":[5],"applications":[6],"ranging":[7],"from":[8,39,61],"job":[9,63],"recommendation":[10],"to":[11,28,35,70,80],"labor":[12],"market":[13],"intelligence,":[14],"is":[15,18],"challenging.Manual":[16],"curation":[17],"slow,":[19],"while":[20],"existing":[21,104],"automated":[22],"methods":[23,105],"are":[24,98],"either":[25],"not":[26],"adaptive":[27],"dynamic":[29],"regional":[30,110],"markets":[31],"(top-down)":[32],"or":[33],"struggle":[34],"build":[36,82],"coherent":[37,84,100],"hierarchies":[38],"noisy":[40],"data":[41],"(bottom-up).":[42],"We":[43,112],"introduce":[44],"CLIMB":[45,65,94],"(CLusterIng-based":[46],"Multi-agent":[47],"taxonomy":[48],"Builder),":[49],"a":[50,76,83],"framework":[51],"that":[52,93,97],"fully":[53],"automates":[54],"the":[55],"creation":[56],"of":[57],"high-quality,":[58],"data-driven":[59],"taxonomies":[60,96],"raw":[62],"postings.":[64],"uses":[66],"global":[67],"semantic":[68],"clustering":[69],"distill":[71],"core":[72],"occupations,":[73],"then":[74],"employs":[75],"reflection-based":[77],"multi-agent":[78],"system":[79],"iteratively":[81],"hierarchy.":[85],"On":[86],"three":[87],"diverse,":[88],"real-world":[89],"datasets,":[90],"we":[91],"show":[92],"produces":[95],"more":[99],"and":[101,106,116],"scalable":[102],"than":[103],"successfully":[107],"capture":[108],"unique":[109],"characteristics.":[111],"release":[113],"our":[114],"code":[115],"datasets":[117],"at":[118],"https://github.com/aida-ugent/CLIMB.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}