{"id":"https://openalex.org/W2105008421","doi":"https://doi.org/10.1145/1835449.1835528","title":"Multi-style language model for web scale information retrieval","display_name":"Multi-style language model for web scale information retrieval","publication_year":2010,"publication_date":"2010-07-19","ids":{"openalex":"https://openalex.org/W2105008421","doi":"https://doi.org/10.1145/1835449.1835528","mag":"2105008421"},"language":"en","primary_location":{"id":"doi:10.1145/1835449.1835528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5041659067","display_name":"Kuansan Wang","orcid":"https://orcid.org/0000-0001-7089-7966"},"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":true,"raw_author_name":"Kuansan Wang","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371535","display_name":"Xiaolong Li","orcid":"https://orcid.org/0000-0001-7493-2650"},"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":"Xiaolong Li","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","Microsoft Redmond, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"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":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041659067"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":7.9132,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97295801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"467","last_page":"474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9970999956130981,"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":0.8533109426498413},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6441608667373657},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6041485071182251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5037173628807068},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5023787021636963},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.46950364112854004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4602870047092438},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43224525451660156},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.41939878463745117},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32269105315208435},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2081693708896637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8533109426498413},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6441608667373657},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6041485071182251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5037173628807068},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5023787021636963},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.46950364112854004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4602870047092438},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43224525451660156},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.41939878463745117},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32269105315208435},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2081693708896637},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1835449.1835528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1835449.1835528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1008.9802","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1008.9802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Xiaolong_Li5/publication/221298948_Multi-style_language_model_for_web_scale_information_retrieval/links/00b4952b92a178822a000000.pdf?origin%3Dpublication_detail","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1011.9239","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1011.9239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Xiaolong_Li5/publication/221298948_Multi-style_language_model_for_web_scale_information_retrieval/links/00b4952b92a178822a000000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.8794","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.8794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/people/jfgao/paper/fp580-wang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W1482214997","https://openalex.org/W1532325895","https://openalex.org/W1797288984","https://openalex.org/W1989468977","https://openalex.org/W2028709054","https://openalex.org/W2032558547","https://openalex.org/W2062270497","https://openalex.org/W2068905009","https://openalex.org/W2069241007","https://openalex.org/W2082729696","https://openalex.org/W2083745421","https://openalex.org/W2084134149","https://openalex.org/W2085030399","https://openalex.org/W2093390569","https://openalex.org/W2095368471","https://openalex.org/W2095683564","https://openalex.org/W2120926619","https://openalex.org/W2134557008","https://openalex.org/W2135322081","https://openalex.org/W2136542423","https://openalex.org/W2136780519","https://openalex.org/W2148212498","https://openalex.org/W2149741699","https://openalex.org/W2151835418","https://openalex.org/W2160825952","https://openalex.org/W2162746367","https://openalex.org/W2165613971","https://openalex.org/W2168859760","https://openalex.org/W2169213601","https://openalex.org/W2169657490","https://openalex.org/W3017143921","https://openalex.org/W4206765718","https://openalex.org/W4213009331","https://openalex.org/W4240913316","https://openalex.org/W4243333943","https://openalex.org/W4245107743","https://openalex.org/W4246858749","https://openalex.org/W6638218882"],"related_works":["https://openalex.org/W1880262756","https://openalex.org/W2062270497","https://openalex.org/W2218559098","https://openalex.org/W2147152072","https://openalex.org/W2107743791","https://openalex.org/W2082718666","https://openalex.org/W1985554184","https://openalex.org/W2139688392","https://openalex.org/W2136583886","https://openalex.org/W2097443371","https://openalex.org/W2093390569","https://openalex.org/W2042980227","https://openalex.org/W1931714234","https://openalex.org/W2136542423","https://openalex.org/W2070740689","https://openalex.org/W2063397738","https://openalex.org/W2165613971","https://openalex.org/W2143331230","https://openalex.org/W2115924763","https://openalex.org/W2006969979"],"abstract_inverted_index":{"Web":[0,80,182,212],"documents":[1],"are":[2,18,118],"typically":[3],"associated":[4,101],"with":[5,93,102,181,201],"many":[6],"text":[7,26,52,99,116],"streams,":[8],"including":[9],"the":[10,12,15,21,24,36,97,103,115,123,130,139,142,158,163,177,185,218,231,235,240],"body,":[11],"title":[13],"and":[14,23,62,125,166,196,204,234],"URL":[16],"that":[17,50,156,176,217],"determined":[19],"by":[20,31,89,230],"authors,":[22],"anchor":[25],"or":[27],"search":[28],"queries":[29],"used":[30],"others":[32],"to":[33,35,55,68,79,96,136,191],"refer":[34],"documents.":[37],"Through":[38],"a":[39,75,90,109],"systematic":[40],"large":[41],"scale":[42,183],"analysis":[43],"on":[44,211],"their":[45,71,167],"cross":[46],"entropy,":[47],"we":[48,149],"show":[49],"these":[51,147],"streams":[53,100,117],"appear":[54],"be":[56,171,198],"composed":[57],"in":[58,83],"different":[59],"language":[60,66,76,160,220],"styles,":[61],"hence":[63],"warrant":[64],"respective":[65],"models":[67,161,221],"properly":[69,137],"describe":[70],"properties.":[72],"We":[73],"propose":[74],"modeling":[77],"approach":[78,178],"document":[81,86,213],"retrieval":[82],"which":[84],"each":[85],"is":[87,189],"characterized":[88],"mixture":[91,110,143,237],"model":[92,111,186,238],"components":[94],"corresponding":[95],"various":[98],"document.":[104],"Immediate":[105],"issues":[106],"for":[107,122],"such":[108],"arise":[112],"as":[113,228],"all":[114,157],"not":[119,128],"always":[120],"present":[121],"documents,":[124],"they":[126],"do":[127],"share":[129],"same":[131,164],"lexicon,":[132],"making":[133],"it":[134],"challenging":[135],"combine":[138],"statistics":[140],"from":[141],"components.":[144],"To":[145,174],"address":[146],"issues,":[148],"introduce":[150],"an":[151],"'open-vocabulary'":[152],"smoothing":[153],"technique":[154],"so":[155],"component":[159,219],"have":[162,223],"cardinality":[165],"scores":[168],"can":[169,179,197],"simply":[170],"linearly":[172],"combined.":[173],"ensure":[175],"cope":[180],"applications,":[184],"training":[187],"algorithm":[188],"designed":[190],"require":[192],"no":[193,205],"labeled":[194],"data":[195],"fully":[199],"automated":[200],"few":[202],"heuristics":[203],"empirical":[206],"parameter":[207],"tunings.":[208],"The":[209],"evaluation":[210],"ranking":[214],"tasks":[215],"shows":[216],"indeed":[222],"varying":[224],"degrees":[225],"of":[226],"capabilities":[227],"predicted":[229],"cross-entropy":[232],"analysis,":[233],"combined":[236],"outperforms":[239],"state-of-the-art":[241],"BM25F":[242],"based":[243],"system.":[244]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}