{"id":"https://openalex.org/W4412888380","doi":"https://doi.org/10.18653/v1/2025.findings-acl.398","title":"Topic Modeling for Short Texts via Optimal Transport-Based Clustering","display_name":"Topic Modeling for Short Texts via Optimal Transport-Based Clustering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888380","doi":"https://doi.org/10.18653/v1/2025.findings-acl.398"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.398","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.398","pdf_url":"https://aclanthology.org/2025.findings-acl.398.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: ACL 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-acl.398.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110616429","display_name":"Tu Vu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu Vu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005908865","display_name":"N. Minh","orcid":"https://orcid.org/0000-0001-5132-4986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manh Do","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111018725","display_name":"Tung Nguyen","orcid":null},"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/A5025948040","display_name":"Dinh Viet Sang","orcid":"https://orcid.org/0000-0002-9254-1327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sang Dinh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026113034","display_name":"Thien Huu Nguyen","orcid":"https://orcid.org/0000-0003-3768-4736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thien Huu Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87764346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7666","last_page":"7680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.991599977016449,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.991599977016449,"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/T10028","display_name":"Topic Modeling","score":0.9876000285148621,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9553999900817871,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034559845924377},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6609011292457581},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36336952447891235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3215973377227783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034559845924377},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6609011292457581},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36336952447891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215973377227783}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.398","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.398","pdf_url":"https://aclanthology.org/2025.findings-acl.398.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.398","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.398","pdf_url":"https://aclanthology.org/2025.findings-acl.398.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5093665582","display_name":"CAREER: Multilingual Learning for Event Structures from  Text","funder_award_id":"2239570","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888380.pdf","grobid_xml":"https://content.openalex.org/works/W4412888380.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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/W3204019825"],"abstract_inverted_index":{"Discovering":[0],"topics":[1],"and":[2,79],"learning":[3,120],"document":[4,39,88],"representations":[5,40,89],"in":[6,17,33,64,90,113,134],"topic":[7,14,23,35,44,92,115,136],"space":[8,93,116],"are":[9],"two":[10],"crucial":[11],"aspects":[12],"of":[13,111,121],"modeling,":[15,36],"particularly":[16],"the":[18,82,91,109,114],"short-text":[19,135],"setting,":[20],"where":[21],"inferring":[22],"proportions":[24],"for":[25],"individual":[26],"documents":[27,112],"is":[28],"highly":[29],"challenging.Despite":[30],"significant":[31],"progress":[32],"neural":[34],"effectively":[37],"distinguishing":[38],"as":[41,43],"well":[42],"embeddings":[45],"remains":[46],"an":[47,70],"open":[48],"problem.In":[49],"this":[50],"paper,":[51],"we":[52,126],"propose":[53],"a":[54],"novel":[55],"method":[56,130],"called":[57],"Enhancing":[58],"Global":[59],"Clustering":[60],"with":[61,94,102],"Optimal":[62,83],"Transport":[63,84],"Topic":[65],"Modeling":[66],"(EnCOT).Our":[67],"approach":[68],"utilizes":[69],"abstract":[71],"global":[72,77,95,100],"clusters":[73,101],"concept":[74],"to":[75,86],"capture":[76],"information":[78],"then":[80],"employs":[81],"framework":[85],"align":[87],"clusters,":[96],"while":[97],"also":[98,118],"aligning":[99],"topics.This":[103],"dual":[104],"alignment":[105],"not":[106],"only":[107],"enhances":[108],"separation":[110],"but":[117],"facilitates":[119],"latent":[122],"topics.Through":[123],"extensive":[124],"experiments,":[125],"demonstrate":[127],"that":[128],"our":[129],"outperforms":[131],"state-of-the-art":[132],"techniques":[133],"modeling":[137],"across":[138],"commonly":[139],"used":[140],"metrics.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}