{"id":"https://openalex.org/W2098876286","doi":"https://doi.org/10.1145/1277741.1277783","title":"Robust classification of rare queries using web knowledge","display_name":"Robust classification of rare queries using web knowledge","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2098876286","doi":"https://doi.org/10.1145/1277741.1277783","mag":"2098876286"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual 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/A5108541542","display_name":"Andrei Broder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":true,"raw_author_name":"Andrei Z. Broder","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073768909","display_name":"Marcus Fontoura","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Marcus Fontoura","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013932834","display_name":"Evgeniy Gabrilovich","orcid":"https://orcid.org/0000-0001-7933-1926"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Evgeniy Gabrilovich","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024420621","display_name":"Amruta Joshi","orcid":"https://orcid.org/0000-0002-9541-1755"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Amruta Joshi","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","orcid":null},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Vanja Josifovski","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558"},"institutions":[{"id":"https://openalex.org/I2800095910","display_name":"Yahoo (Spain)","ror":"https://ror.org/03gq8sg42","country_code":"ES","type":"company","lineage":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"]},{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["ES","US"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["Yahoo Research","Yahoo! research,"],"affiliations":[{"raw_affiliation_string":"Yahoo Research","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! research,","institution_ids":["https://openalex.org/I2800095910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5108541542"],"corresponding_institution_ids":["https://openalex.org/I2800095910","https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":38.7697,"has_fulltext":false,"cited_by_count":180,"citation_normalized_percentile":{"value":0.99714059,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9962000250816345,"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":0.9930999875068665,"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":0.8430243730545044},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.8018079400062561},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.7383163571357727},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7041213512420654},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.690656304359436},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.653536856174469},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5684887766838074},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5062938928604126},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5011918544769287},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4612983167171478},{"id":"https://openalex.org/keywords/online-aggregation","display_name":"Online aggregation","score":0.42765629291534424},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4142836332321167},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.41002756357192993},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3952714204788208},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24213510751724243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430243730545044},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.8018079400062561},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.7383163571357727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7041213512420654},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.690656304359436},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.653536856174469},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5684887766838074},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5062938928604126},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5011918544769287},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4612983167171478},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.42765629291534424},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4142836332321167},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.41002756357192993},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3952714204788208},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24213510751724243},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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":3,"locations":[{"id":"doi:10.1145/1277741.1277783","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277783","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-98348","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-98348","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-98348","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-98348","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W103965747","https://openalex.org/W150304357","https://openalex.org/W1481308070","https://openalex.org/W1482214997","https://openalex.org/W1538556863","https://openalex.org/W1557757161","https://openalex.org/W1972640883","https://openalex.org/W1985182453","https://openalex.org/W1985554184","https://openalex.org/W1986475174","https://openalex.org/W1998548536","https://openalex.org/W1999817920","https://openalex.org/W2000672666","https://openalex.org/W2000826169","https://openalex.org/W2002306339","https://openalex.org/W2002388301","https://openalex.org/W2034927834","https://openalex.org/W2066343754","https://openalex.org/W2084134149","https://openalex.org/W2105106523","https://openalex.org/W2155540986","https://openalex.org/W2162993204","https://openalex.org/W2164547069","https://openalex.org/W2486357588","https://openalex.org/W2797692640","https://openalex.org/W3017143921","https://openalex.org/W4251560691","https://openalex.org/W4296980202","https://openalex.org/W6628905179","https://openalex.org/W6684151790","https://openalex.org/W6776565550"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W3125756434","https://openalex.org/W1560919561","https://openalex.org/W1793997780","https://openalex.org/W185198413","https://openalex.org/W2013069866","https://openalex.org/W2041106684","https://openalex.org/W2538384344","https://openalex.org/W2186703450","https://openalex.org/W2168049757"],"abstract_inverted_index":{"We":[0,36,111],"propose":[1],"a":[2,6,31,38,43,89,103,131],"methodology":[3,101,116],"for":[4,88],"building":[5],"practical":[7],"robust":[8],"query":[9,17,28],"classification":[10,106],"system":[11],"that":[12,99,113],"can":[13],"identify":[14],"thousands":[15],"of":[16,30,63,79,81,92,122],"classes":[18],"with":[19,26],"reasonable":[20],"accuracy,":[21],"while":[22],"dealing":[23],"in":[24,85],"real-time":[25],"the":[27,51,57,61,74,77,114],"volume":[29],"commercial":[32],"web":[33,52],"search":[34,53,64,93],"engine.":[35],"use":[37],"blind":[39],"feedback":[40],"technique:":[41],"given":[42],"query,":[44],"we":[45,66],"determine":[46],"its":[47],"topic":[48],"by":[49,56,60],"classifying":[50],"results":[54],"retrieved":[55],"query.":[58],"Motivated":[59],"needs":[62],"advertising,":[65],"primarily":[67],"focus":[68],"on":[69],"rare":[70,126],"queries,":[71],"which":[72],"are":[73],"hardest":[75],"from":[76],"point":[78],"view":[80],"machine":[82],"learning,":[83],"yet":[84],"aggregation":[86],"account":[87],"considerable":[90],"fraction":[91],"engine":[94],"traffic.":[95],"Empirical":[96],"evaluation":[97],"confirms":[98],"our":[100],"yields":[102],"considerably":[104],"higher":[105],"accuracy":[107],"than":[108],"previously":[109],"reported.":[110],"believe":[112],"proposed":[115],"will":[117],"lead":[118],"to":[119,125,130],"better":[120,132],"matching":[121],"online":[123],"ads":[124],"queries":[127],"and":[128],"overall":[129],"user":[133],"experience.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":20}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
