{"id":"https://openalex.org/W4416033912","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1107","title":"ProtoXTM: Cross-Lingual Topic Modeling with Document-Level Prototype-based Contrastive Learning","display_name":"ProtoXTM: Cross-Lingual Topic Modeling with Document-Level Prototype-based Contrastive Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033912","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1107"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1107","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1107.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108330279","display_name":"Seungwon Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Won Seo","raw_affiliation_strings":["Department of Mathematics Ajou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics Ajou University","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076655220","display_name":"Soon-Sun Kwon","orcid":"https://orcid.org/0000-0002-3344-1609"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soon-Sun Kwon","raw_affiliation_strings":["Department of Mathematics Ajou University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics Ajou University","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15671192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20340","last_page":"20354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2004999965429306,"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":0.2004999965429306,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.17270000278949738,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.10890000313520432,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5217999815940857},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.44920000433921814},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3873000144958496},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.30309998989105225},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161999702453613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5040000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1107","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1107","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1107.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3638702923","display_name":null,"funder_award_id":"RS-2021-NR060141","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033912.pdf","grobid_xml":"https://content.openalex.org/works/W4416033912.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-Lingual":[0],"Topic":[1],"Modeling":[2],"(CLTM)":[3],"is":[4],"an":[5],"essential":[6],"task":[7],"in":[8,30,49,88],"the":[9,53,58,82],"field":[10],"of":[11,60,84],"data":[12,125],"mining":[13],"and":[14,22,57,81,151],"natural":[15],"language":[16],"processing,":[17],"aiming":[18],"to":[19,40,64],"extract":[20],"aligned":[21],"semantically":[23,74],"coherent":[24,75],"topics":[25,76],"from":[26],"bilingual":[27,38],"corpora.Recent":[28],"advances":[29],"crosslingual":[31,131,150],"neural":[32,132],"topic":[33,43,51,54,62,86,93,112,133,156],"models":[34],"have":[35],"widely":[36],"leveraged":[37],"dictionaries":[39],"achieve":[41],"wordlevel":[42],"alignment.However,":[44],"two":[45],"critical":[46],"challenges":[47],"remain":[48],"cross-lingual":[50,85,111],"modeling,":[52],"mismatch":[55],"issue":[56],"degeneration":[59],"intra-lingual":[61],"interpretability.Due":[63],"linguistic":[65],"diversity,":[66],"some":[67],"translated":[68],"word":[69],"pairs":[70],"may":[71],"not":[72],"represent":[73],"despite":[77],"being":[78],"lexical":[79],"equivalents,":[80],"objective":[83],"alignment":[87],"CLTM":[89],"can":[90],"consequently":[91],"degrade":[92],"interpretability":[94],"within":[95],"each":[96],"intralanguages.To":[97],"address":[98],"these":[99],"issues,":[100],"we":[101,114,127],"propose":[102],"a":[103,116,130],"novel":[104],"document-level":[105],"prototype-based":[106,138],"contrastive":[107,122,139],"learning":[108,123],"paradigm":[109],"for":[110,121],"modeling.Additionally,":[113],"design":[115],"retrieval-based":[117],"positive":[118],"sampling":[119],"strategy":[120],"without":[124],"augmentation.Furthermore,":[126],"introduce":[128],"ProtoXTM,":[129],"model":[134],"based":[135],"on":[136,149],"documentlevel":[137],"learning.Extensive":[140],"experiments":[141],"indicate":[142],"that":[143],"our":[144],"approach":[145],"achieves":[146],"state-of-the-art":[147],"performance":[148],"mono-lingual":[152],"benchmarks,":[153],"demonstrating":[154],"enhanced":[155],"interpretability.":[157]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}