{"id":"https://openalex.org/W2025653016","doi":"https://doi.org/10.1145/1143844.1143881","title":"Clustering documents with an exponential-family approximation of the Dirichlet compound multinomial distribution","display_name":"Clustering documents with an exponential-family approximation of the Dirichlet compound multinomial distribution","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2025653016","doi":"https://doi.org/10.1145/1143844.1143881","mag":"2025653016"},"language":"en","primary_location":{"id":"doi:10.1145/1143844.1143881","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143881","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/A5038246567","display_name":"Charles Elkan","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charles Elkan","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge MA and University of California, San Diego, La Jolla, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge MA and University of California, San Diego, La Jolla, CA","institution_ids":["https://openalex.org/I36258959","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038246567"],"corresponding_institution_ids":["https://openalex.org/I36258959","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":8.7938,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.98499084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9986000061035156,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9986000061035156,"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":0.9950000047683716,"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":0.9940999746322632,"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/multinomial-distribution","display_name":"Multinomial distribution","score":0.7931324243545532},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.7585399746894836},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7445845603942871},{"id":"https://openalex.org/keywords/exponential-family","display_name":"Exponential family","score":0.6489066481590271},{"id":"https://openalex.org/keywords/laplace-distribution","display_name":"Laplace distribution","score":0.5868479609489441},{"id":"https://openalex.org/keywords/burstiness","display_name":"Burstiness","score":0.580382227897644},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5743581652641296},{"id":"https://openalex.org/keywords/heavy-tailed-distribution","display_name":"Heavy-tailed distribution","score":0.48693525791168213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4721139669418335},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.45867568254470825},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4566660225391388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40420955419540405},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3837396502494812},{"id":"https://openalex.org/keywords/exponential-distribution","display_name":"Exponential distribution","score":0.3538537323474884},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3359484076499939},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.32032009959220886},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25595489144325256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2190215289592743},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.15554609894752502},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.12905395030975342},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08979684114456177}],"concepts":[{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.7931324243545532},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.7585399746894836},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7445845603942871},{"id":"https://openalex.org/C55974624","wikidata":"https://www.wikidata.org/wiki/Q1188504","display_name":"Exponential family","level":2,"score":0.6489066481590271},{"id":"https://openalex.org/C183057437","wikidata":"https://www.wikidata.org/wiki/Q671617","display_name":"Laplace distribution","level":3,"score":0.5868479609489441},{"id":"https://openalex.org/C2781023610","wikidata":"https://www.wikidata.org/wiki/Q17006304","display_name":"Burstiness","level":3,"score":0.580382227897644},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5743581652641296},{"id":"https://openalex.org/C1602530","wikidata":"https://www.wikidata.org/wiki/Q1472677","display_name":"Heavy-tailed distribution","level":3,"score":0.48693525791168213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4721139669418335},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.45867568254470825},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4566660225391388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40420955419540405},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3837396502494812},{"id":"https://openalex.org/C55350006","wikidata":"https://www.wikidata.org/wiki/Q237193","display_name":"Exponential distribution","level":2,"score":0.3538537323474884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3359484076499939},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.32032009959220886},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25595489144325256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2190215289592743},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.15554609894752502},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.12905395030975342},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08979684114456177},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1143844.1143881","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1143844.1143881","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.6624","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.6624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-cse.ucsd.edu/users/elkan/edcm.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.6164","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.6164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://imls.engr.oregonstate.edu/www/htdocs/proceedings/icml2006/037_Clustering_Documents.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W181283514","https://openalex.org/W190008395","https://openalex.org/W1522930108","https://openalex.org/W1880262756","https://openalex.org/W1981081578","https://openalex.org/W2007463795","https://openalex.org/W2038303880","https://openalex.org/W2096765209","https://openalex.org/W2112050062","https://openalex.org/W2130695933","https://openalex.org/W2135631383","https://openalex.org/W2145001205","https://openalex.org/W2159399018","https://openalex.org/W2166468440","https://openalex.org/W2801179766","https://openalex.org/W3016843226"],"related_works":["https://openalex.org/W2155374833","https://openalex.org/W4235791879","https://openalex.org/W4210340638","https://openalex.org/W4253842653","https://openalex.org/W208947034","https://openalex.org/W1968944308","https://openalex.org/W2044705817","https://openalex.org/W2724279847","https://openalex.org/W1969763686","https://openalex.org/W2088126627"],"abstract_inverted_index":{"The":[0],"Dirichlet":[1],"compound":[2],"multinomial":[3],"(DCM)":[4],"distribution,":[5,11],"also":[6],"called":[7],"the":[8,23,71,91,117,123,127,132],"multivariate":[9],"Polya":[10],"is":[12,35,86,120],"a":[13,27,32,42,108],"model":[14],"for":[15,81,94,112],"text":[16],"documents":[17],"that":[18,25,47,85,116],"takes":[19],"into":[20,70],"account":[21],"burstiness:":[22],"fact":[24],"if":[26],"word":[28],"occurs":[29],"once":[30],"in":[31,126],"document,":[33],"it":[34],"likely":[36],"to":[37,50,67],"occur":[38],"repeatedly.":[39],"We":[40,61],"derive":[41,78],"new":[43,109,118],"family":[44],"of":[45,73,134,136],"distributions":[46,52,66],"are":[48],"approximations":[49],"DCM":[51,59,74,95],"and":[53,76,104,129],"constitute":[54],"an":[55,79],"exponential":[56],"family,":[57],"unlike":[58],"distributions.":[60,96],"use":[62],"these":[63],"so-called":[64],"EDCM":[65,82,102],"obtain":[68],"insights":[69],"properties":[72],"distributions,":[75],"then":[77],"algorithm":[80,111,119],"maximum-likelihood":[83],"training":[84],"many":[87],"times":[88],"faster":[89],"than":[90],"corresponding":[92],"method":[93],"Next,":[97],"we":[98],"investigate":[99],"expectation-maximization":[100],"with":[101,122,139],"components":[103],"deterministic":[105],"annealing":[106],"as":[107],"clustering":[110],"documents.":[113],"Experiments":[114],"show":[115],"competitive":[121],"best":[124],"methods":[125],"literature,":[128],"superior":[130],"from":[131],"point":[133],"view":[135],"finding":[137],"models":[138],"low":[140],"perplexity.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}