{"id":"https://openalex.org/W2891418927","doi":"https://doi.org/10.1145/3234944.3234975","title":"StatBM25","display_name":"StatBM25","publication_year":2018,"publication_date":"2018-09-10","ids":{"openalex":"https://openalex.org/W2891418927","doi":"https://doi.org/10.1145/3234944.3234975","mag":"2891418927"},"language":"en","primary_location":{"id":"doi:10.1145/3234944.3234975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234944.3234975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of 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/A5026852283","display_name":"Xing Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xing Tan","raw_affiliation_strings":["York University, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006513566","display_name":"Fanghong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanghong Jiang","raw_affiliation_strings":["Central China Normal University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Central China Normal University, Wuhan, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000409439","display_name":"Jimmy Xiangji Huang","orcid":"https://orcid.org/0000-0003-1292-1491"},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Xiangji Huang","raw_affiliation_strings":["York University, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Toronto, Canada","institution_ids":["https://openalex.org/I192455969"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026852283"],"corresponding_institution_ids":["https://openalex.org/I192455969"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12047176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9979000091552734,"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/T11106","display_name":"Data Management and Algorithms","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9914000034332275,"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/computer-science","display_name":"Computer science","score":0.7224891185760498},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6561620235443115},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5899313688278198},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.519950270652771},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5060040354728699},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.44250357151031494},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4276488125324249},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3470381796360016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28260302543640137},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2555517554283142},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24590694904327393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224891185760498},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6561620235443115},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5899313688278198},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.519950270652771},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5060040354728699},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.44250357151031494},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4276488125324249},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3470381796360016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28260302543640137},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2555517554283142},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24590694904327393},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3234944.3234975","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234944.3234975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W2014415866","https://openalex.org/W2034707531","https://openalex.org/W2052842594","https://openalex.org/W2060494110","https://openalex.org/W2079980096","https://openalex.org/W2080068076","https://openalex.org/W2112006025","https://openalex.org/W2127020676","https://openalex.org/W2146081744","https://openalex.org/W2170907675","https://openalex.org/W2263798363","https://openalex.org/W2469689378","https://openalex.org/W2758481792","https://openalex.org/W3150942237","https://openalex.org/W4230706820"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2787352659","https://openalex.org/W1970611213","https://openalex.org/W4206560911","https://openalex.org/W2090097149"],"abstract_inverted_index":{"In":[0],"Information":[1],"Retrieval":[2],"and":[3,19,27,33,52,186,202],"Web":[4],"Search,":[5],"BM25":[6,21,64],"is":[7,65,98,113,128,135,149,163],"one":[8],"of":[9,35,92,105,183,212],"the":[10,83,90,102,106,141,144,158,166],"most":[11],"influential":[12],"probabilistic":[13],"retrieval":[14],"formulas":[15],"for":[16,56,217],"document":[17,37,42,54,57,218],"weighting":[18],"ranking.":[20,58,219],"involves":[22],"three":[23],"parameters":[24],"$k_1$,":[25],"$k_3$":[26],"b,":[28],"which":[29,75],"provide":[30],"scalar":[31],"approximation":[32],"scaling":[34],"important":[36],"features":[38,55],"such":[39],"asterm":[40],"frequency,":[41,43],"anddocument":[44],"length.":[45],"We":[46],"investigate":[47],"in":[48,69,89,138,157,165,193],"this":[49],"paper":[50],"aggregative":[51,71],"statistical":[53,118,161],"Shortly":[59],"speaking,":[60],"a":[61,110,122,199],"statistically":[62,200],"adjusted":[63],"used":[66,129],"to":[67,95,101,153,189,205,210],"score":[68],"an":[70,99],"way":[72],"onvirtual":[73],"documents,":[74],"are":[76,170],"generated":[77],"by":[78],"randomly":[79],"combining":[80],"documents":[81,94],"from":[82],"original":[84,107,145],"collection.":[85],"The":[86],"problem":[87,103,146],"size,":[88],"number":[91],"virtual":[93],"be":[96,154],"ranked,":[97],"expansion":[100],"size":[104],"problem.":[108],"As":[109],"result,":[111],"ranking":[112],"actually":[114],"realized":[115],"through":[116],"performing":[117],"sampling.":[119],"Rejection":[120],"Sampling,":[121],"simple":[123],"Monte":[124],"Carlo":[125],"sampling":[126,162],"method":[127],"at":[130],"present.":[131],"This":[132,191],"new":[133,214],"framework":[134],"called":[136],"StatBM25,":[137],"emphasizing":[139],"first":[140],"fact":[142],"that":[143,196],"domain":[147],"space":[148],"K-expanded":[150],"(a":[151],"concept":[152],"further":[155],"explained":[156],"paper);":[159],"Further,":[160],"employed":[164],"model.":[167],"Empirical":[168],"studies":[169],"performed":[171],"on":[172],"several":[173],"standard":[174],"test":[175],"collections,":[176],"where":[177],"StatBM25":[178,197],"demonstrates":[179],"convincingly":[180],"high":[181],"degree":[182],"both":[184],"uniqueness":[185],"effectiveness":[187],"compared":[188],"BM25.":[190],"means,":[192],"our":[194],"belief,":[195],"as":[198],"smoothed":[201],"normalized":[203],"variant":[204],"BM25,":[206],"might":[207],"eventually":[208],"lead":[209],"discoveries":[211],"useful":[213],"statistic":[215],"measures":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-09-27T00:00:00"}