{"id":"https://openalex.org/W2104210067","doi":"https://doi.org/10.1145/1143844.1143967","title":"Topic modeling","display_name":"Topic modeling","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2104210067","doi":"https://doi.org/10.1145/1143844.1143967","mag":"2104210067"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning - ICML '06","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046348432","display_name":"Hanna Wallach","orcid":"https://orcid.org/0000-0003-3395-7186"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hanna M. Wallach","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046348432"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1068,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"984"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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/bigram","display_name":"Bigram","score":0.9613058567047119},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.762915849685669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606759667396545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6698675751686096},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6365958452224731},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6364415884017944},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6241304278373718},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5496287941932678},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.5403301119804382},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5249238610267639},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.501072883605957},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4637497067451477},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4345918297767639},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.41128242015838623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32010751962661743},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.1734933853149414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1533840000629425}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9613058567047119},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.762915849685669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606759667396545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6698675751686096},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6365958452224731},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6364415884017944},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6241304278373718},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5496287941932678},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.5403301119804382},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5249238610267639},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.501072883605957},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4637497067451477},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4345918297767639},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.41128242015838623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32010751962661743},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.1734933853149414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1533840000629425},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1143844.1143967","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Machine learning - ICML '06","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W190008395","https://openalex.org/W1597533204","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2027255954","https://openalex.org/W2112971401","https://openalex.org/W2132957691","https://openalex.org/W2135194391"],"related_works":["https://openalex.org/W1551384396","https://openalex.org/W3191364917","https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2940857995","https://openalex.org/W2251863249","https://openalex.org/W2096865229","https://openalex.org/W4291700620","https://openalex.org/W2096610504","https://openalex.org/W2390209509"],"abstract_inverted_index":{"Some":[0],"models":[1],"of":[2,64,86],"textual":[3],"corpora":[4],"employ":[5],"text":[6],"generation":[7],"methods":[8,31],"involving":[9],"n-gram":[10,49],"statistics,":[11,125],"while":[12],"others":[13],"use":[14],"latent":[15,52],"topic":[16,53,59,107],"variables":[17,54],"inferred":[18,75,111],"using":[19,76,123],"the":[20,89,110],"\"bag-of-words\"":[21],"assumption,":[22],"in":[23],"which":[24],"word":[25],"order":[26],"is":[27],"ignored.":[28],"Previously,":[29],"these":[30],"have":[32],"not":[33],"been":[34],"combined.":[35],"In":[36],"this":[37],"work,":[38],"I":[39],"explore":[40],"a":[41,57,65,77,98,105],"hierarchical":[42,66,99],"generative":[43],"probabilistic":[44],"model":[45,60,72,91,103],"that":[46],"incorporates":[47],"both":[48],"statistics":[50],"and":[51],"by":[55,116],"extending":[56],"unigram":[58,106,124],"to":[61],"include":[62],"properties":[63],"Dirichlet":[67,100],"bigram":[68,101],"language":[69,102],"model.":[70,108],"The":[71],"hyperparameters":[73],"are":[74,113,120],"Gibbs":[78],"EM":[79],"algorithm.":[80],"On":[81],"two":[82],"data":[83],"sets,":[84],"each":[85],"150":[87],"documents,":[88],"new":[90],"exhibits":[92],"better":[93],"predictive":[94],"accuracy":[95],"than":[96,119],"either":[97],"or":[104],"Additionally,":[109],"topics":[112,121],"less":[114],"dominated":[115],"function":[117],"words":[118],"discovered":[122],"potentially":[126],"making":[127],"them":[128],"more":[129],"meaningful.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":81},{"year":2020,"cited_by_count":105},{"year":2019,"cited_by_count":89},{"year":2018,"cited_by_count":80},{"year":2017,"cited_by_count":75},{"year":2016,"cited_by_count":76},{"year":2015,"cited_by_count":105},{"year":2014,"cited_by_count":64},{"year":2013,"cited_by_count":57},{"year":2012,"cited_by_count":48}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2016-06-24T00:00:00"}