{"id":"https://openalex.org/W4409671212","doi":"https://doi.org/10.1145/3696410.3714690","title":"Compress and Mix: Advancing Efficient Taxonomy Completion with Large Language Models","display_name":"Compress and Mix: Advancing Efficient Taxonomy Completion with Large Language Models","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409671212","doi":"https://doi.org/10.1145/3696410.3714690"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714690","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","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/10.1145/3696410.3714690","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hongyuan Xu","orcid":"https://orcid.org/0009-0000-5278-0457"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongyuan Xu","raw_affiliation_strings":["TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117249510","display_name":"Yuhang Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Niu","raw_affiliation_strings":["TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103172652","display_name":"Yanlong Wen","orcid":"https://orcid.org/0000-0002-8006-9109"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlong Wen","raw_affiliation_strings":["TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062064974","display_name":"Xiaojie Yuan","orcid":"https://orcid.org/0000-0002-5876-6856"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Yuan","raw_affiliation_strings":["TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"TMCC &amp; TBI Center, College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":7.0294,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96277108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4239","last_page":"4249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9970999956130981,"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":0.8080958127975464},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.47689107060432434},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.39407116174697876},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.390961229801178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080958127975464},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.47689107060432434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.39407116174697876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.390961229801178},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696410.3714690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714690","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696410.3714690","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696410.3714690","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696410.3714690","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G212106316","display_name":null,"funder_award_id":"72342017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4667360632","display_name":null,"funder_award_id":"62372252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323021","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409671212.pdf","grobid_xml":"https://content.openalex.org/works/W4409671212.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2144005186","https://openalex.org/W2164480198","https://openalex.org/W2187089797","https://openalex.org/W2473007590","https://openalex.org/W2493916176","https://openalex.org/W2606611007","https://openalex.org/W2765407302","https://openalex.org/W2946532448","https://openalex.org/W2995837271","https://openalex.org/W3012615229","https://openalex.org/W3012823870","https://openalex.org/W3100195825","https://openalex.org/W3152722128","https://openalex.org/W3168349005","https://openalex.org/W3173065403","https://openalex.org/W3174311454","https://openalex.org/W3176459892","https://openalex.org/W3199714630","https://openalex.org/W3212837704","https://openalex.org/W4221153270","https://openalex.org/W4224326644","https://openalex.org/W4285602055","https://openalex.org/W4290874851","https://openalex.org/W4313118352","https://openalex.org/W4367047009","https://openalex.org/W4367047185","https://openalex.org/W4386071700","https://openalex.org/W4386566662","https://openalex.org/W4386721807","https://openalex.org/W4388018335","https://openalex.org/W4389524473","https://openalex.org/W4396758735","https://openalex.org/W4400524696","https://openalex.org/W4401024576","https://openalex.org/W4401863567","https://openalex.org/W4402183970","https://openalex.org/W4402671368","https://openalex.org/W4402671764","https://openalex.org/W4402671839"],"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":{"Taxonomy":[0],"completion":[1,45],"aims":[2],"to":[3,31,53,73,125,146,151],"integrate":[4],"new":[5],"concepts":[6],"into":[7,68],"existing":[8,27],"taxonomies":[9],"by":[10],"determining":[11],"their":[12],"appropriate":[13],"hypernym":[14],"and":[15,19,57,108,121,158],"hyponym.":[16],"While":[17],"semantic":[18,56,120],"structural":[20,58,122],"information":[21,59],"are":[22,161],"crucial":[23],"for":[24],"this":[25,37],"task,":[26],"approaches":[28],"often":[29],"struggle":[30],"balance":[32],"these":[33,81,113],"aspects":[34],"effectively.":[35],"In":[36],"paper,":[38],"we":[39],"propose":[40],"COMI,":[41],"an":[42],"efficient":[43],"taxonomy":[44,128],"framework":[46],"that":[47,138],"leverages":[48],"large":[49],"language":[50],"models":[51],"(LLMs)":[52],"capture":[54],"both":[55],"in":[60],"a":[61,91],"unified":[62],"manner.":[63],"COMI":[64,115,139],"<u>co</u>mpresses":[65],"node":[66],"semantics":[67],"token":[69],"representations,":[70],"enabling":[71],"LLMs":[72],"efficiently":[74],"process":[75,94],"the":[76,85,89,117,152],"input":[77],"structure":[78],"composed":[79],"of":[80,88,119],"tokens.":[82],"To":[83],"enhance":[84],"model's":[86],"understanding":[87],"structure,":[90],"further":[92],"fine-tuning":[93],"using":[95],"contrastive":[96],"learning":[97],"with":[98],"<u>mi</u>xup":[99],"data":[100],"augmentation":[101],"is":[102],"applied,":[103],"where":[104],"mixup":[105],"generates":[106],"diverse":[107],"challenging":[109],"negative":[110],"samples.":[111],"Through":[112],"innovations,":[114],"improves":[116],"integration":[118],"information,":[123],"leading":[124],"more":[126],"accurate":[127],"completion.":[129],"The":[130],"experimental":[131],"results":[132],"on":[133],"three":[134],"real-world":[135],"datasets":[136],"demonstrate":[137],"achieves":[140],"state-of-the-art":[141],"performance":[142],"while":[143],"showing":[144],"up":[145],"284x":[147],"faster":[148],"inference":[149],"compared":[150],"previous":[153],"best":[154],"method.":[155],"Our":[156],"code":[157],"compressed":[159],"tokens":[160],"available":[162],"at":[163],"https://github.com/cyclexu/COMI.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}