{"id":"https://openalex.org/W2745475103","doi":"https://doi.org/10.1145/3091108","title":"Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings","display_name":"Enhancing Topic Modeling for Short Texts with Auxiliary Word Embeddings","publication_year":2017,"publication_date":"2017-08-21","ids":{"openalex":"https://openalex.org/W2745475103","doi":"https://doi.org/10.1145/3091108","mag":"2745475103"},"language":"en","primary_location":{"id":"doi:10.1145/3091108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3091108","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100734069","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0003-3144-6374"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006827289","display_name":"Yu Duan","orcid":"https://orcid.org/0000-0003-1113-7953"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Duan","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324815","display_name":"Haoran Wang","orcid":"https://orcid.org/0000-0001-8733-9266"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754253","display_name":"Zhiqian Zhang","orcid":"https://orcid.org/0000-0002-1542-7491"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqian Zhang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618738","display_name":"Aixin Sun","orcid":"https://orcid.org/0000-0003-0764-4258"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Aixin Sun","raw_affiliation_strings":["Nanyang Technological University, Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008327536","display_name":"Zongyang Ma","orcid":"https://orcid.org/0009-0003-1980-9379"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zongyang Ma","raw_affiliation_strings":["Nanyang Technological University, Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.9629,"has_fulltext":false,"cited_by_count":142,"citation_normalized_percentile":{"value":0.98791165,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"36","issue":"2","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9933000206947327,"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":0.9926999807357788,"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":0.8393276333808899},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.712952733039856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6760902404785156},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6631761789321899},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.646687924861908},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6120010614395142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5878763198852539},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47251591086387634},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44065001606941223},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4173714518547058},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.286359041929245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393276333808899},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.712952733039856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6760902404785156},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6631761789321899},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.646687924861908},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6120010614395142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5878763198852539},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47251591086387634},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44065001606941223},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4173714518547058},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.286359041929245},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3091108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3091108","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7050358598","display_name":null,"funder_award_id":"61502344","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W27263903","https://openalex.org/W43037342","https://openalex.org/W100623710","https://openalex.org/W658020064","https://openalex.org/W1572401739","https://openalex.org/W1608334810","https://openalex.org/W1614298861","https://openalex.org/W1714665356","https://openalex.org/W1847760371","https://openalex.org/W1880262756","https://openalex.org/W1973289172","https://openalex.org/W1986188181","https://openalex.org/W1995866178","https://openalex.org/W2003184546","https://openalex.org/W2004192095","https://openalex.org/W2028742638","https://openalex.org/W2044185127","https://openalex.org/W2048195127","https://openalex.org/W2053968437","https://openalex.org/W2061922307","https://openalex.org/W2063904635","https://openalex.org/W2076219102","https://openalex.org/W2097089247","https://openalex.org/W2098824882","https://openalex.org/W2107743791","https://openalex.org/W2117130368","https://openalex.org/W2130284530","https://openalex.org/W2130339025","https://openalex.org/W2131462252","https://openalex.org/W2135790056","https://openalex.org/W2137958601","https://openalex.org/W2139317750","https://openalex.org/W2146341620","https://openalex.org/W2147946282","https://openalex.org/W2151703435","https://openalex.org/W2152253130","https://openalex.org/W2158899491","https://openalex.org/W2159426623","https://openalex.org/W2166008115","https://openalex.org/W2168332560","https://openalex.org/W2171836785","https://openalex.org/W2178725228","https://openalex.org/W2222893162","https://openalex.org/W2250539671","https://openalex.org/W2250753706","https://openalex.org/W2252172130","https://openalex.org/W2340381866","https://openalex.org/W2514450663","https://openalex.org/W2516537890","https://openalex.org/W2997617958","https://openalex.org/W4233135949","https://openalex.org/W6600459194"],"related_works":["https://openalex.org/W2251363724","https://openalex.org/W1983719983","https://openalex.org/W2970121487","https://openalex.org/W4309940794","https://openalex.org/W2971876279","https://openalex.org/W3031970385","https://openalex.org/W2163194442","https://openalex.org/W4302211199","https://openalex.org/W2370554703","https://openalex.org/W3102628894"],"abstract_inverted_index":{"Many":[0],"applications":[1],"require":[2],"semantic":[3,196,227,239,291],"understanding":[4,215],"of":[5,38,45,56,82,114,119,126,171,211,237,296,396],"short":[6,48,75,83,107,128,162,202,212,308,328,340],"texts,":[7,329],"and":[8,11,18,123,332,380,386],"inferring":[9],"discriminative":[10],"coherent":[12],"latent":[13],"topics":[14,34,172],"is":[15,69,85,121,130,180,216],"a":[16,36,88,157,168,205,209,242,370],"critical":[17],"fundamental":[19],"task":[20],"in":[21,54,231,343,369],"these":[22],"applications.":[23],"Conventional":[24],"topic":[25,72,112,154,270,305,325,352,359,363,384],"models":[26,326],"largely":[27],"rely":[28],"on":[29,220,337],"word":[30,57,232,238,247,290],"co-occurrences":[31],"to":[32,42,103,151,164,175,192,251,261,303,366],"derive":[33],"from":[35,241,294],"collection":[37],"documents.":[39],"However,":[40,91],"due":[41],"the":[43,63,117,124,127,135,153,214,253,263,268,272,277,284,313,317,394],"length":[44,125],"each":[46,80,106,161],"document,":[47],"texts":[49,76,129],"are":[50],"much":[51],"more":[52,323],"sparse":[53],"terms":[55],"co-occurrences.":[58],"Recent":[59,229],"studies":[60],"show":[61],"that":[62,79,105,348],"Dirichlet":[64],"Multinomial":[65],"Mixture":[66],"(DMM)":[67],"model":[68,152,179,315],"effective":[70,235,324],"for":[71,142,307,327],"inference":[73],"over":[74],"by":[77,87,275,358],"assuming":[78],"piece":[81,210],"text":[84,108,163,341,371,387],"generated":[86],"single":[89],"topic.":[90],"DMM":[92,184],"has":[93,109],"two":[94,322,338,344],"main":[95],"limitations.":[96],"First,":[97],"even":[98],"though":[99],"it":[100],"seems":[101],"reasonable":[102],"assume":[104],"only":[110],"one":[111,174],"because":[113],"its":[115,221],"shortness,":[116],"definition":[118],"\u201cshortness\u201d":[120],"subjective":[122],"dataset":[131],"dependent.":[132],"That":[133],"is,":[134],"single-topic":[136],"assumption":[137],"may":[138],"be":[139,165,300],"too":[140],"strong":[141],"some":[143],"datasets.":[144],"To":[145,256],"address":[146,252],"this":[147,257],"limitation,":[148],"we":[149,259,320,346],"propose":[150,260,321],"number":[155,170],"as":[156,374],"Poisson":[158],"distribution,":[159],"allowing":[160],"associated":[166],"with":[167,316],"small":[169],"(e.g.,":[173,195],"three":[176],"topics).":[177],"This":[178],"named":[181,330],"PDMM.":[182],"Second,":[183],"(and":[185],"also":[186,225],"PDMM)":[187],"does":[188],"not":[189,217],"have":[190],"access":[191],"background":[193,287],"knowledge":[194,288],"relations":[197,240,292],"between":[198],"words)":[199],"when":[200],"modeling":[201,306],"texts.":[203,309],"When":[204],"human":[206],"being":[207],"interprets":[208],"text,":[213],"solely":[218],"based":[219],"content":[222],"words,":[223],"but":[224],"their":[226],"relations.":[228],"advances":[230],"embeddings":[233,248],"offer":[234],"learning":[236],"large":[243],"corpus.":[244],"Such":[245],"auxiliary":[246],"enable":[249],"us":[250],"second":[254],"limitation.":[255],"end,":[258],"promote":[262],"semantically":[264],"related":[265],"words":[266],"under":[267],"same":[269],"during":[271],"sampling":[273],"process,":[274],"using":[276],"generalized":[278],"P\u00f3lya":[279],"urn":[280],"(GPU)":[281],"model.":[282],"Through":[283,334],"GPU":[285,318],"model,":[286,319],"about":[289],"learned":[293,362],"millions":[295],"external":[297],"documents":[298],"can":[299],"easily":[301],"exploited":[302],"improve":[304,383],"By":[310],"directly":[311],"extending":[312],"PDMM":[314,349],"GPU-DMM":[331,379,392],"GPU-PDMM.":[333],"extensive":[335],"experiments":[336],"real-world":[339],"collections":[342],"languages,":[345],"demonstrate":[347],"achieves":[350],"better":[351,367],"representations":[353],"than":[354],"state-of-the-art":[355],"models,":[356],"measured":[357],"coherence.":[360],"The":[361],"representation":[364],"leads":[365],"accuracy":[368],"classification":[372,388],"task,":[373],"an":[375],"indirect":[376],"evaluation.":[377],"Both":[378],"GPU-PDMM":[381,390],"further":[382],"coherence":[385],"accuracy.":[389],"outperforms":[391],"at":[393],"price":[395],"higher":[397],"computational":[398],"costs.":[399]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":18}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}