{"id":"https://openalex.org/W1539587635","doi":"https://doi.org/10.1145/2746231","title":"A P\u00f3lya Urn Document Language Model for Improved Information Retrieval","display_name":"A P\u00f3lya Urn Document Language Model for Improved Information Retrieval","publication_year":2015,"publication_date":"2015-05-04","ids":{"openalex":"https://openalex.org/W1539587635","doi":"https://doi.org/10.1145/2746231","mag":"1539587635"},"language":"en","primary_location":{"id":"doi:10.1145/2746231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2746231","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/A5073506203","display_name":"Ronan Cummins","orcid":"https://orcid.org/0000-0001-9404-4220"},"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":false,"raw_author_name":"Ronan Cummins","raw_affiliation_strings":["University of Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062553068","display_name":"Jiaul H. Paik","orcid":"https://orcid.org/0000-0003-1550-3586"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaul H. Paik","raw_affiliation_strings":["University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045898854","display_name":"Yuanhua Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanhua Lv","raw_affiliation_strings":["Microsoft Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.548,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96543892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":"4","first_page":"1","last_page":"34"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/burstiness","display_name":"Burstiness","score":0.9513118863105774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8406341075897217},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7328652739524841},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.5567606091499329},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.521019697189331},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.494735449552536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858491122722626},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.47725340723991394},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4103964865207672},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.11516046524047852},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08880561590194702}],"concepts":[{"id":"https://openalex.org/C2781023610","wikidata":"https://www.wikidata.org/wiki/Q17006304","display_name":"Burstiness","level":3,"score":0.9513118863105774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406341075897217},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7328652739524841},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.5567606091499329},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.521019697189331},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.494735449552536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858491122722626},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.47725340723991394},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4103964865207672},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.11516046524047852},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08880561590194702},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2746231","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2746231","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W190008395","https://openalex.org/W211275634","https://openalex.org/W1482214997","https://openalex.org/W1513915383","https://openalex.org/W1514144124","https://openalex.org/W1763381236","https://openalex.org/W1838897829","https://openalex.org/W1964348731","https://openalex.org/W1964675638","https://openalex.org/W1966093341","https://openalex.org/W1967193210","https://openalex.org/W1972594981","https://openalex.org/W1973234918","https://openalex.org/W1973878062","https://openalex.org/W1979963107","https://openalex.org/W1981159181","https://openalex.org/W1981200123","https://openalex.org/W1985471546","https://openalex.org/W1993692165","https://openalex.org/W1993803315","https://openalex.org/W1999822363","https://openalex.org/W2000569744","https://openalex.org/W2005545412","https://openalex.org/W2009593660","https://openalex.org/W2010291682","https://openalex.org/W2014415866","https://openalex.org/W2024932032","https://openalex.org/W2025653016","https://openalex.org/W2029212055","https://openalex.org/W2036671379","https://openalex.org/W2042980227","https://openalex.org/W2044490427","https://openalex.org/W2046902062","https://openalex.org/W2062173014","https://openalex.org/W2070740689","https://openalex.org/W2073051407","https://openalex.org/W2080068076","https://openalex.org/W2087173123","https://openalex.org/W2093390569","https://openalex.org/W2099871636","https://openalex.org/W2105157020","https://openalex.org/W2115760558","https://openalex.org/W2117473841","https://openalex.org/W2131924950","https://openalex.org/W2134557008","https://openalex.org/W2135631383","https://openalex.org/W2136542423","https://openalex.org/W2142769902","https://openalex.org/W2142846455","https://openalex.org/W2144211451","https://openalex.org/W2144656525","https://openalex.org/W2145037371","https://openalex.org/W2153252192","https://openalex.org/W2153479077","https://openalex.org/W2154848821","https://openalex.org/W2160825952","https://openalex.org/W2161852686","https://openalex.org/W2162697159","https://openalex.org/W2168859760","https://openalex.org/W2169213601","https://openalex.org/W2296285930","https://openalex.org/W2605800822","https://openalex.org/W4206765718","https://openalex.org/W4234200495","https://openalex.org/W4238346259","https://openalex.org/W4240913316","https://openalex.org/W4246858749","https://openalex.org/W4250467157"],"related_works":["https://openalex.org/W1843717240","https://openalex.org/W2340440348","https://openalex.org/W2083756677","https://openalex.org/W2737070158","https://openalex.org/W2508200300","https://openalex.org/W4297850514","https://openalex.org/W2138256111","https://openalex.org/W2600332032","https://openalex.org/W2953283456","https://openalex.org/W1539587635"],"abstract_inverted_index":{"The":[0],"multinomial":[1,21,71,141],"language":[2,72,85,114,142,169],"model":[3,25,53,73,86,115,133,158,170],"has":[4],"been":[5],"one":[6,26],"of":[7,12,37,103,119],"the":[8,20,35,82,112,127,131,140,150,156,161,167,185],"most":[9],"effective":[10],"models":[11],"retrieval":[13,94],"for":[14,116,149,183],"more":[15,135],"than":[16,137],"a":[17,38,44,57,68,117,147,173],"decade.":[18],"However,":[19],"distribution":[22],"does":[23],"not":[24],"important":[27],"linguistic":[28],"phenomenon":[29],"relating":[30],"to":[31,40,160,177],"term":[32,39,186],"dependency\u2014that":[33],"is,":[34],"tendency":[36],"repeat":[41],"itself":[42],"within":[43],"document":[45,54,188],"(i.e.,":[46],"word":[47,76],"burstiness).":[48],"In":[49],"this":[50],"article,":[51],"we":[52,106,145,164],"generation":[55],"as":[56,90,92],"random":[58],"process":[59],"with":[60,97],"reinforcement":[61],"(a":[62],"multivariate":[63],"P\u00f3lya":[64],"process)":[65],"and":[66,96,153,187],"develop":[67,146],"Dirichlet":[69],"compound":[70],"that":[74,81,108,126,138,155,166],"captures":[75],"burstiness":[77],"directly.":[78],"We":[79],"show":[80,107,125,154,165],"new":[83,168],"reinforced":[84],"can":[87],"be":[88],"computed":[89],"efficiently":[91],"current":[93],"models,":[95],"experiments":[98],"on":[99],"an":[100],"extensive":[101],"set":[102],"TREC":[104],"collections,":[105],"it":[109],"significantly":[110],"outperforms":[111],"state-of-the-art":[113],"number":[118],"standard":[120],"effectiveness":[121],"metrics.":[122],"Experiments":[123],"also":[124],"tuning":[128],"parameter":[129],"in":[130,139,191],"proposed":[132,157],"is":[134],"robust":[136],"model.":[143],"Furthermore,":[144],"constraint":[148],"verbosity":[151],"hypothesis":[152],"adheres":[159],"constraint.":[162],"Finally,":[163],"essentially":[171],"introduces":[172],"measure":[174],"closely":[175],"related":[176],"idf,":[178],"which":[179],"gives":[180],"theoretical":[181],"justification":[182],"combining":[184],"event":[189],"spaces":[190],"tf-idf":[192],"type":[193],"schemes.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}