{"id":"https://openalex.org/W2068905009","doi":"https://doi.org/10.1145/3130348.3130375","title":"Document Language Models, Query Models, and Risk Minimization for Information Retrieval","display_name":"Document Language Models, Query Models, and Risk Minimization for Information Retrieval","publication_year":2017,"publication_date":"2017-08-02","ids":{"openalex":"https://openalex.org/W2068905009","doi":"https://doi.org/10.1145/3130348.3130375","mag":"2068905009"},"language":"en","primary_location":{"id":"doi:10.1145/3130348.3130375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3130348.3130375","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","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/A5060219657","display_name":"John Lafferty","orcid":"https://orcid.org/0000-0002-5929-220X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Lafferty","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028518494","display_name":"ChengXiang Zhai","orcid":"https://orcid.org/0000-0002-6434-3702"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengxiang Zhai","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060219657"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":42.981,"has_fulltext":false,"cited_by_count":773,"citation_normalized_percentile":{"value":0.99791697,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"51","issue":"2","first_page":"251","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9965999722480774,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8935360312461853},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.7568484544754028},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.7517686486244202},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6611870527267456},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.629244327545166},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.619756281375885},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.588140606880188},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5765019059181213},{"id":"https://openalex.org/keywords/rdf-query-language","display_name":"RDF query language","score":0.5400351881980896},{"id":"https://openalex.org/keywords/divergence-from-randomness-model","display_name":"Divergence-from-randomness model","score":0.4604616165161133},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.4519323408603668},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.43694227933883667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.366049587726593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34872332215309143},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.3392760753631592},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3270612359046936},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2069942057132721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8935360312461853},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.7568484544754028},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.7517686486244202},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6611870527267456},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.629244327545166},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.619756281375885},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.588140606880188},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5765019059181213},{"id":"https://openalex.org/C96956885","wikidata":"https://www.wikidata.org/wiki/Q6138701","display_name":"RDF query language","level":5,"score":0.5400351881980896},{"id":"https://openalex.org/C149189445","wikidata":"https://www.wikidata.org/wiki/Q5283894","display_name":"Divergence-from-randomness model","level":3,"score":0.4604616165161133},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.4519323408603668},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.43694227933883667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.366049587726593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34872332215309143},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3392760753631592},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3270612359046936},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2069942057132721}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3130348.3130375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3130348.3130375","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.4641","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.4641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aladdin.cs.cmu.edu/papers/pdfs/y2001/risk.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.305.347","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.305.347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.407.7432","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.407.7432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iro.umontreal.ca/~nie/IFT6255/lafferty-zhai.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.116","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/afs/cs/project/link-3/lafferty/www/ps/risk.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1482214997","https://openalex.org/W1540124269","https://openalex.org/W1809658417","https://openalex.org/W1982442952","https://openalex.org/W1997600320","https://openalex.org/W2026417691","https://openalex.org/W2038925774","https://openalex.org/W2043909051","https://openalex.org/W2046657015","https://openalex.org/W2051629332","https://openalex.org/W2062270497","https://openalex.org/W2066636486","https://openalex.org/W2093390569","https://openalex.org/W2095368471","https://openalex.org/W2102046030","https://openalex.org/W2136729221","https://openalex.org/W2138621811","https://openalex.org/W2147152072","https://openalex.org/W2153890685","https://openalex.org/W2160484851","https://openalex.org/W2621280964","https://openalex.org/W4206765718","https://openalex.org/W4245107743","https://openalex.org/W6628905179","https://openalex.org/W6632313116"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2572349046","https://openalex.org/W2169498276","https://openalex.org/W2538384344","https://openalex.org/W2026738364","https://openalex.org/W2146885082","https://openalex.org/W2013069866","https://openalex.org/W2124814993","https://openalex.org/W1984397732","https://openalex.org/W2392799717"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,15,54,85,104,112],"framework":[3,25],"for":[4,46,57,99,170,180],"information":[5,41],"retrieval":[6,29,62],"that":[7,31],"combines":[8],"document":[9,48],"models":[10,13,98,154],"and":[11,60,88,132,143,151],"query":[12,72,119,157,167],"using":[14,107,159],"probabilistic":[16],"ranking":[17],"function":[18],"based":[19],"on":[20,111,140,183],"Bayesian":[21],"decision":[22],"theory.":[23],"The":[24,71,121,135],"suggests":[26],"an":[27],"operational":[28],"model":[30,45,56,74,79],"extends":[32],"recent":[33,92],"developments":[34],"in":[35,66],"the":[36,61,82,118,146,176],"language":[37,44,55,73,148],"modeling":[38,149],"approach":[39,137,150],"to":[40,78,116,127,145],"retrieval.":[42],"A":[43],"each":[47,58],"is":[49,64,138],"estimated,":[50],"as":[51,53],"well":[52],"query,":[59,86],"problem":[63],"cast":[65],"terms":[67],"of":[68,84,114],"risk":[69],"minimization.":[70],"can":[75],"be":[76],"exploited":[77],"user":[80],"preferences,":[81],"context":[83],"synonomy":[87],"word":[89,96],"senses.":[90],"While":[91],"work":[93],"has":[94,125],"incorporated":[95],"translation":[97],"this":[100],"purpose,":[101],"we":[102],"introduce":[103],"new":[105,136],"method":[106,124],"Markov":[108,122],"chains":[109],"defined":[110],"set":[113],"documents":[115],"estimate":[117],"models.":[120],"chain":[123],"connections":[126],"algorithms":[128],"from":[129],"link":[130],"analysis":[131],"social":[133],"networks.":[134],"evaluated":[139],"TREC":[141],"collections":[142],"compared":[144],"basic":[147],"vector":[152],"space":[153],"together":[155],"with":[156,175],"expansion":[158,168],"Rocchio.":[160],"Significant":[161],"improvements":[162,178],"are":[163],"obtained":[164],"over":[165],"standard":[166],"methods":[169],"strong":[171],"baseline":[172],"TF-IDF":[173],"systems,":[174],"greatest":[177],"attained":[179],"short":[181],"queries":[182],"Web":[184],"data.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":32},{"year":2015,"cited_by_count":28},{"year":2014,"cited_by_count":47},{"year":2013,"cited_by_count":37},{"year":2012,"cited_by_count":61}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}