{"id":"https://openalex.org/W2111875680","doi":"https://doi.org/10.1145/1076034.1076114","title":"A study of the dirichlet priors for term frequency normalisation","display_name":"A study of the dirichlet priors for term frequency normalisation","publication_year":2005,"publication_date":"2005-08-15","ids":{"openalex":"https://openalex.org/W2111875680","doi":"https://doi.org/10.1145/1076034.1076114","mag":"2111875680"},"language":"en","primary_location":{"id":"doi:10.1145/1076034.1076114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5109888639","display_name":"Ben He","orcid":"https://orcid.org/0000-0002-2699-9209"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben He","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom","University of Glasgow, Glasgow, United Kingdom#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom#TAB#","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iadh Ounis","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom","University of Glasgow, Glasgow, United Kingdom#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom#TAB#","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":1.9716,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.87420942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"465","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9965999722480774,"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/prior-probability","display_name":"Prior probability","score":0.8854479789733887},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.7753406167030334},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6804324984550476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5697852969169617},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5340828895568848},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5328940153121948},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.4867546558380127},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.477193683385849},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.43032407760620117},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4191930294036865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3905296325683594},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3508806526660919},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33844131231307983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31496304273605347},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.2464788258075714},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1581517457962036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08382084965705872}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8854479789733887},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.7753406167030334},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6804324984550476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5697852969169617},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5340828895568848},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5328940153121948},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.4867546558380127},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.477193683385849},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.43032407760620117},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4191930294036865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3905296325683594},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3508806526660919},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33844131231307983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31496304273605347},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2464788258075714},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1581517457962036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08382084965705872},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1076034.1076114","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1076034.1076114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:3549","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.4519","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.4519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ir.dcs.gla.ac.uk/smooth/f219-he.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.323.9015","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.323.9015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://terrierteam.dcs.gla.ac.uk/publications/he05study-of-dirichlet-priors.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.8228","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.8228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.gla.ac.uk/3549/01/he3549.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"},{"id":"https://openalex.org/F4320320337","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1482214997","https://openalex.org/W1509991416","https://openalex.org/W1597533204","https://openalex.org/W1974413746","https://openalex.org/W2000569744","https://openalex.org/W2097927681","https://openalex.org/W2105157020","https://openalex.org/W2105380208","https://openalex.org/W2133986984","https://openalex.org/W2136542423","https://openalex.org/W2144211451","https://openalex.org/W2587628976","https://openalex.org/W2950186769","https://openalex.org/W3150555252","https://openalex.org/W4234200495","https://openalex.org/W4235264713","https://openalex.org/W4240913316","https://openalex.org/W4245920622","https://openalex.org/W4256537130","https://openalex.org/W6628905179","https://openalex.org/W6630516739","https://openalex.org/W7052201853"],"related_works":["https://openalex.org/W2497860580","https://openalex.org/W2891616219","https://openalex.org/W2914864478","https://openalex.org/W2097627380","https://openalex.org/W2796920963","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W3204672119","https://openalex.org/W22044811"],"abstract_inverted_index":{"In":[0,19],"Information":[1],"Retrieval":[2],"(IR),":[3],"the":[4,11,15,24,28,33,39,63,69,88,93,104,108],"Dirichlet":[5,25,70,94,111],"Priors":[6,26,71,95],"have":[7],"been":[8],"applied":[9],"to":[10,27,67,87],"smoothing":[12],"technique":[13],"of":[14,32,47,92,107],"language":[16],"modeling":[17],"approach.":[18],"this":[20,48,100],"paper,":[21],"we":[22,60,81],"apply":[23],"term":[29],"frequency":[30],"normalisation":[31,72],"classical":[34],"BM25":[35],"probabilistic":[36],"model":[37],"and":[38,77],"Divergence":[40],"from":[41],"Randomness":[42],"PL2":[43],"model.":[44],"The":[45],"contributions":[46],"paper":[49],"are":[50],"twofold.":[51],"First,":[52],"through":[53],"extensive":[54],"experiments":[55],"on":[56],"four":[57],"TREC":[58],"collections,":[59],"show":[61,98],"that":[62,99],"newly":[64,109],"generated":[65,110],"models,":[66],"which":[68],"is":[73],"applied,":[74],"provide":[75],"robust":[76],"effective":[78],"performance.":[79],"Second,":[80],"propose":[82],"a":[83],"novel":[84],"theoretically-driven":[85],"approach":[86,102],"automatic":[89],"parameter":[90],"tuning":[91,101],"normalisation.":[96],"Experiments":[97],"optimises":[103],"retrieval":[105],"performance":[106],"Priors-based":[112],"weighting":[113],"models.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}