{"id":"https://openalex.org/W2010291682","doi":"https://doi.org/10.1145/1008992.1009122","title":"Information retrieval using hierarchical dirichlet processes","display_name":"Information retrieval using hierarchical dirichlet processes","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2010291682","doi":"https://doi.org/10.1145/1008992.1009122","mag":"2010291682"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-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/A5073624135","display_name":"Philip J. Cowans","orcid":null},"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":"Philip J. Cowans","raw_affiliation_strings":["University of Cambridge, Cambridge, UK"],"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/A5073624135"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.9243,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.81138309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"564","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9987000226974487,"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":0.9987000226974487,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11106","display_name":"Data Management and Algorithms","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/weighting","display_name":"Weighting","score":0.7517159581184387},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7087372541427612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6951116919517517},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.6259028911590576},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.575311005115509},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5519523024559021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5415617823600769},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4856339991092682},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4471929371356964},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.41937530040740967},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4116780459880829},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.4110007584095001},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3627467453479767},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34620577096939087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25846725702285767},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.2455541491508484},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16587883234024048}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7517159581184387},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7087372541427612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951116919517517},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.6259028911590576},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.575311005115509},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5519523024559021},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5415617823600769},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4856339991092682},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4471929371356964},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.41937530040740967},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4116780459880829},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.4110007584095001},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3627467453479767},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34620577096939087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25846725702285767},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2455541491508484},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16587883234024048},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1008992.1009122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.6383","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.6383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.inference.phy.cam.ac.uk/pjc51/publications/sigir04.ps","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":5,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1540124269","https://openalex.org/W2093390569","https://openalex.org/W2158266063","https://openalex.org/W4206765718"],"related_works":["https://openalex.org/W3121467232","https://openalex.org/W2393894849","https://openalex.org/W2107192713","https://openalex.org/W2027714503","https://openalex.org/W2544994990","https://openalex.org/W4254467987","https://openalex.org/W3190171609","https://openalex.org/W1531847006","https://openalex.org/W2170902875","https://openalex.org/W2005265490"],"abstract_inverted_index":{"An":[0],"information":[1],"retrieval":[2],"method":[3,25,49],"is":[4,50,65],"proposed":[5],"using":[6],"a":[7,12,18,28],"hierarchical":[8],"Dirichlet":[9],"process":[10],"as":[11],"prior":[13],"on":[14,61],"the":[15,57],"parameters":[16],"of":[17,20,30],"set":[19],"multinomial":[21],"distributions.":[22],"The":[23,47],"resulting":[24],"naturally":[26],"includes":[27],"number":[29],"features":[31],"found":[32],"in":[33],"other":[34],"popular":[35],"methods.":[36],"Specifically,":[37],"tf.idf-like":[38],"term":[39],"weighting":[40],"and":[41,56,64],"document":[42],"length":[43],"normalisation":[44],"are":[45],"recovered.":[46],"new":[48],"compared":[51],"with":[52],"Okapi":[53],"BM-25":[54],"[3]":[55],"Twenty-One":[58],"model":[59],"[1]":[60],"TREC":[62],"data":[63],"shown":[66],"to":[67],"give":[68],"better":[69],"performance.":[70]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}