{"id":"https://openalex.org/W7224426150","doi":"https://doi.org/10.18653/2026.findings-emnlp.1364","title":"Vendi Clustering for Diversity-Preserving Topic Reduction","display_name":"Vendi Clustering for Diversity-Preserving Topic Reduction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224426150","doi":"https://doi.org/10.18653/2026.findings-emnlp.1364"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1364","doi":"https://doi.org/10.18653/2026.findings-emnlp.1364","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1364","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1364.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1364.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104264965","display_name":"Sean Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Kim","raw_affiliation_strings":["Brown University","Vertaix"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Vertaix","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063448291","display_name":"Adji Bousso Dieng","orcid":"https://orcid.org/0000-0001-5687-3554","observed_orcids":["https://orcid.org/0000-0001-5687-3554"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adji Bousso Dieng","raw_affiliation_strings":["Princeton University","Vertaix"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Vertaix","institution_ids":[]}]}],"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":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28964","last_page":"28980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9916999936103821,"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":0.9916999936103821,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.002899999963119626,"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":0.00279999990016222,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/topic-clustering","display_name":"topic clustering","score":0.7049999833106995},{"id":"https://openalex.org/keywords/topic-diversity","display_name":"topic diversity","score":0.675000011920929},{"id":"https://openalex.org/keywords/bertopic","display_name":"BERTopic","score":0.7269999980926514},{"id":"https://openalex.org/keywords/computational-cost-reduction","display_name":"computational complexity reduction","score":0.6200000047683716},{"id":"https://openalex.org/keywords/gram-matrix","display_name":"Gram matrix","score":0.6050000190734863},{"id":"https://openalex.org/keywords/topic-coherence","display_name":"topic coherence","score":0.5720000267028809},{"id":"https://openalex.org/keywords/outlier-removal","display_name":"outlier removal","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6080999970436096},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46389999985694885},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25040000677108765},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1364","doi":"https://doi.org/10.18653/2026.findings-emnlp.1364","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1364","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1364.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.1364","doi":"https://doi.org/10.18653/2026.findings-emnlp.1364","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1364","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1364.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224426150.pdf","grobid_xml":"https://content.openalex.org/works/W7224426150.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2786672974","https://openalex.org/W3080951367","https://openalex.org/W4221142221","https://openalex.org/W4416255953"],"related_works":["https://openalex.org/W4412944965","https://openalex.org/W7043733258","https://openalex.org/W2284317161","https://openalex.org/W7011315686","https://openalex.org/W7027206766","https://openalex.org/W7096692119","https://openalex.org/W7033072561","https://openalex.org/W3093579662","https://openalex.org/W3005978461","https://openalex.org/W2287227970"],"abstract_inverted_index":{"Embedding-based":[0],"topic":[1,43,155],"models":[2],"such":[3],"as":[4,50],"BERTopic":[5],"routinely":[6],"produce":[7],"hundreds":[8],"of":[9,73,77,142,158],"finegrained,":[10],"overlapping":[11],"topics":[12],"that":[13,46,61,97],"must":[14],"be":[15],"reduced":[16],"before":[17],"downstream":[18],"use.Existing":[19],"approaches":[20],"couple":[21],"reduction":[22,44,130,138],"with":[23,154],"outlier":[24],"rejection,":[25],"rely":[26],"on":[27,132,139],"local":[28],"geometric":[29],"linkage,":[30],"or":[31],"use":[32],"costly":[33],"and":[34,108,124,134,149],"stochastic":[35],"LLM":[36],"prompting.We":[37],"introduce":[38],"Vendi":[39,68],"Clustering":[40],"(VC),":[41],"a":[42,70,109,117,150],"method":[45],"reframes":[47],"the":[48,59,63,67,140],"problem":[49],"global":[51,79],"diversity-preserving":[52],"compression:":[53],"at":[54,83,92],"each":[55,99],"step,":[56],"VC":[57,127],"selects":[58],"merge":[60,101],"induces":[62],"smallest":[64],"loss":[65],"in":[66,102],"Score,":[69],"spectral":[71],"measure":[72],"diversity.A":[74],"naive":[75],"implementation":[76],"this":[78],"criterion":[80],"is":[81],"prohibitive":[82],"O(n":[84,119],"6":[85],");":[86],"we":[87],"derive":[88],"algebraic":[89],"update":[90],"rules":[91],"order":[93],"q":[94],"=":[95],"2":[96],"evaluate":[98],"candidate":[100],"O(1)":[103],"via":[104],"cached":[105],"row-square":[106],"sums":[107],"lookahead":[110],"Gram":[111],"matrix,":[112],"reducing":[113],"total":[114],"complexity":[115],"to":[116,160],"tractable":[118],"3":[120],").On":[121],"20":[122],"Newsgroups":[123],"AG":[125],"News,":[126],"outperforms":[128],"standard":[129],"baselines":[131],"coherence":[133],"diversity,":[135],"surpasses":[136],"LLM-prompted":[137],"majority":[141],"metrics":[143],"against":[144],"both":[145],"an":[146],"open-weight":[147],"model":[148],"frontier":[151],"API":[152],"model,":[153],"diversity":[156],"gains":[157],"up":[159],"35%":[161],"while":[162],"running":[163],"over":[164],"40\u00d7":[165],"faster.":[166]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-30T00:00:00"}