{"id":"https://openalex.org/W4416035009","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.298","title":"XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments","display_name":"XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035009","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.298"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.298","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.298","pdf_url":"https://aclanthology.org/2025.findings-emnlp.298.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.298.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113374892","display_name":"Tien Phat Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien Phat Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ngo Vu Minh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngo Vu Minh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100642009","display_name":"Tung Nguyen","orcid":"https://orcid.org/0000-0003-4232-0566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tung Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022485068","display_name":"Linh Ngo Van","orcid":"https://orcid.org/0000-0002-0011-5137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linh Ngo Van","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101999873","display_name":"\u0110\u1ee9c Anh Nguy\u1ec5n","orcid":"https://orcid.org/0000-0002-9856-2110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc Anh Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025948040","display_name":"Dinh Viet Sang","orcid":"https://orcid.org/0000-0002-9254-1327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinh Viet Sang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102780660","display_name":"Trung Le","orcid":"https://orcid.org/0000-0003-0414-9067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trung Le","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5561","last_page":"5575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2883000075817108,"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":0.2883000075817108,"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":0.2305999994277954,"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":0.0982000008225441,"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":0.6927000284194946},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.34599998593330383},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.30469998717308044},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.29760000109672546}],"concepts":[{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825000047683716},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6028000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514999985694885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3959999978542328},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.298","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.298","pdf_url":"https://aclanthology.org/2025.findings-emnlp.298.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.298","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.298","pdf_url":"https://aclanthology.org/2025.findings-emnlp.298.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035009.pdf","grobid_xml":"https://content.openalex.org/works/W4416035009.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-lingual":[0],"topic":[1,32,40,87,128],"modeling":[2,63],"aims":[3],"to":[4,15,37,96,104],"uncover":[5],"shared":[6,82],"semantic":[7,83],"themes":[8],"across":[9,45,115],"languages.Several":[10],"methods":[11,26],"have":[12,27],"been":[13],"proposed":[14],"address":[16],"this":[17],"problem,":[18],"leveraging":[19],"both":[20],"traditional":[21],"and":[22,42,54,85,111,113,131,134],"neural":[23],"approaches.While":[24],"previous":[25],"achieved":[28],"some":[29],"improvements":[30],"in":[31,80,127],"diversity,":[33,130],"they":[34],"often":[35],"struggle":[36],"ensure":[38],"high":[39],"coherence":[41],"consistent":[43],"alignment":[44,132],"languages.We":[46],"propose":[47],"XTRA":[48,103,122],"(Cross-Lingual":[49],"Topic":[50,53],"Modeling":[51],"with":[52,64],"Representation":[55],"Alignments),":[56],"a":[57,81],"novel":[58],"framework":[59],"that":[60,107,121],"unifies":[61],"Bag-of-Words":[62],"multilingual":[65,118],"embeddings.XTRA":[66],"introduces":[67],"two":[68],"core":[69],"components:":[70],"(1)":[71],"representation":[72],"alignment,":[73,88],"aligning":[74],"document-topic":[75],"distributions":[76,91],"via":[77],"contrastive":[78],"learning":[79],"space;":[84],"(2)":[86],"projecting":[89],"topic-word":[90],"into":[92],"the":[93],"same":[94],"space":[95],"enforce":[97],"crosslingual":[98],"consistency.This":[99],"dual":[100],"mechanism":[101],"enables":[102],"learn":[105],"topics":[106],"are":[108,137],"interpretable":[109],"(coherent":[110],"diverse)":[112],"wellaligned":[114],"languages.Experiments":[116],"on":[117],"corpora":[119],"confirm":[120],"significantly":[123],"outperforms":[124],"strong":[125],"baselines":[126],"coherence,":[129],"quality.Code":[133],"reproducible":[135],"scripts":[136],"available":[138],"at":[139],"https:":[140],"//github.com/tienphat140205/XTRA.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}