{"id":"https://openalex.org/W2251007793","doi":null,"title":"Topic Models, Latent Space Models, Sparse Coding, and All That: A Systematic Understanding of Probabilistic Semantic Extraction in Large Corpus","display_name":"Topic Models, Latent Space Models, Sparse Coding, and All That: A Systematic Understanding of Probabilistic Semantic Extraction in Large Corpus","publication_year":2012,"publication_date":"2012-07-08","ids":{"openalex":"https://openalex.org/W2251007793","mag":"2251007793"},"language":"en","primary_location":{"id":"mag:2251007793","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/P12-4003/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Meeting of the Association for Computational Linguistics","raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eric P. Xing","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":"https://orcid.org/0009-0005-9158-4201","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5009547049"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18026329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"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":0.9937000274658203,"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":0.003000000026077032,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.000699999975040555,"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/topic-modeling","display_name":"topic modeling","score":0.781000018119812},{"id":"https://openalex.org/keywords/latent-space-models","display_name":"latent space models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/sparse-coding","display_name":"sparse coding","score":0.9959999918937683},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"latent Dirichlet allocation","score":0.8799999952316284},{"id":"https://openalex.org/keywords/admixture-model","display_name":"admixture model","score":0.8960000276565552},{"id":"https://openalex.org/keywords/mixed-membership-models","display_name":"mixed membership models","score":0.9929999709129333},{"id":"https://openalex.org/keywords/probabilistic-graphical-models","display_name":"probabilistic graphical models","score":0.968999981880188},{"id":"https://openalex.org/keywords/latent-semantic-indexing","display_name":"latent semantic indexing","score":0.7749999761581421},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"non-negative matrix factorization","score":0.9800000190734863},{"id":"https://openalex.org/keywords/semantic-information-extraction","display_name":"semantic information extraction","score":0.45899999141693115},{"id":"https://openalex.org/keywords/multimodal-data","display_name":"multimodal data","score":0.7749999761581421},{"id":"https://openalex.org/keywords/supervised-topic-models","display_name":"supervised topic models","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857402563095093},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7854118347167969},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.7252314686775208},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5544680953025818},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.523979127407074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055191516876221},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4834080934524536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4748518764972687},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4558687210083008},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4462076723575592},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.44202110171318054},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4134840965270996},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4013713300228119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38724285364151},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2251007793","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/P12-4003/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Meeting of the Association for Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2279018116","https://openalex.org/W2395962679","https://openalex.org/W7100325050","https://openalex.org/W2741257866","https://openalex.org/W2810633914","https://openalex.org/W28821396","https://openalex.org/W2001097032","https://openalex.org/W4205693635","https://openalex.org/W7161733837","https://openalex.org/W2038162821"],"abstract_inverted_index":{"Probabilistic":[0],"topic":[1,71,82,105,135,168,183],"models":[2,72,106,169,289,311],"have":[3],"recently":[4],"gained":[5],"much":[6],"popularity":[7],"in":[8,100,118,144,195,245,317],"informational":[9],"retrieval":[10],"and":[11,37,55,59,76,89,130,159,170,185,210,218,232,239,247,263,283,312,322],"related":[12,90,192,314],"areas.":[13],"Via":[14],"such":[15,22,96,112,127,164,198],"models,":[16,209],"one":[17],"can":[18,39,56],"project":[19],"high-dimensional":[20],"objects":[21],"as":[23,97,113,128,199,299],"text":[24,117],"documents":[25],"into":[26],"a":[27,51,81,145,175,189,216,258,273,300,318],"low":[28],"dimensional":[29],"space":[30,208,230],"where":[31],"their":[32,171],"latent":[33,207,229],"semantics":[34],"are":[35],"captured":[36],"modeled;":[38],"integrate":[40],"multiple":[41],"sources":[42],"of":[43,50,125,178,182,191,221,236,252,261,280,291],"information---to":[44],"share":[45],"statistical":[46],"strength":[47],"among":[48],"components":[49],"hierarchical":[52],"probabilistic":[269],"model;":[54],"structurally":[57],"display":[58],"classify":[60],"the":[61,156,167,179,200,226,234,268,277,306,310,313],"otherwise":[62],"unstructured":[63],"object":[64],"collections.":[65],"However,":[66],"to":[67,75,78,91,103,107,133,188,286,303],"many":[68],"practitioners,":[69],"how":[70,84,102,132],"work,":[73],"what":[74],"not":[77],"expect":[79],"from":[80,88],"model,":[83,203,206],"is":[85],"it":[86],"different":[87,243],"classical":[92],"matrix":[93],"algebraic":[94],"techniques":[95,224],"LSI,":[98],"NMF":[99],"NLP,":[101],"empower":[104],"deal":[108],"with":[109],"complex":[110,288],"scenarios":[111],"multimodal":[114],"data,":[115,142],"contractual":[116],"social":[119],"media,":[120],"evolving":[121],"corpus,":[122],"or":[123],"presence":[124],"supervision":[126],"labeling":[129],"rating,":[131],"make":[134],"modeling":[136],"computationally":[137],"tractable":[138],"even":[139],"on":[140,267],"web-scale":[141],"etc.,":[143],"principled":[146],"way,":[147],"remain":[148],"unclear.":[149],"In":[150],"this":[151,253,297],"tutorial,":[152],"I":[153,213,294],"will":[154,214,265,295],"demystify":[155],"conceptual,":[157],"mathematical,":[158],"computational":[160,315],"issues":[161,262,316],"behind":[162],"all":[163,222],"problems":[165,264],"surrounding":[166],"applications":[172,244],"by":[173],"presenting":[174],"systematic":[176],"overview":[177],"mathematical":[180,307],"foundation":[181],"modeling,":[184],"its":[186],"connections":[187],"number":[190],"methods":[193],"popular":[194],"other":[196],"fields":[197],"LDA,":[201],"admixture":[202],"mixed":[204],"membership":[205],"sparse":[211],"coding.":[212],"offer":[215],"simple":[217],"unifying":[219],"view":[220],"these":[223],"under":[225],"framework":[227],"multi-view":[228],"embedding,":[231],"online":[233],"roadmap":[235],"model":[271],"extension":[238],"algorithmic":[240],"design":[241],"toward":[242],"IR":[246],"NLP.":[248],"A":[249],"main":[250,301],"theme":[251],"tutorial":[254],"that":[255,275],"tie":[256],"together":[257],"wide":[259],"range":[260],"build":[266,287],"graphical":[270],"formalism,":[272],"formalism":[274,298],"exploits":[276],"conjoined":[278],"talents":[279],"graph":[281],"theory":[282,285],"probability":[284],"out":[290],"simpler":[292],"pieces.":[293],"use":[296],"aid":[302],"discuss":[304],"both":[305],"underpinnings":[308],"for":[309],"unified,":[319],"simplistic,":[320],"transparent,":[321],"actionable":[323],"fashion.":[324]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}