{"id":"https://openalex.org/W2087084609","doi":"https://doi.org/10.1145/1498759.1498811","title":"Cross-language query classification using web search for exogenous knowledge","display_name":"Cross-language query classification using web search for exogenous knowledge","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W2087084609","doi":"https://doi.org/10.1145/1498759.1498811","mag":"2087084609"},"language":"en","primary_location":{"id":"doi:10.1145/1498759.1498811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","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/A5012483706","display_name":"Xuerui Wang","orcid":"https://orcid.org/0000-0001-8938-3420"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuerui Wang","raw_affiliation_strings":["University of Massachusetts, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrei Broder","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evgeniy Gabrilovich","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037908462","display_name":"Vanja Josifovski","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vanja Josifovski","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058655480","display_name":"Bo Pang","orcid":"https://orcid.org/0000-0002-4359-2937"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Pang","raw_affiliation_strings":["Yahoo! Research, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, CA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1057,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93248031,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"74","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9876999855041504,"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":0.9876999855041504,"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":0.9800999760627747,"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":0.9631999731063843,"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":0.885427713394165},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.6340420246124268},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5980485677719116},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.587955117225647},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.572435200214386},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5606083273887634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557995617389679},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5489552021026611},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.45854878425598145},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.45252978801727295},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.42870235443115234},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37578096985816956},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2182631492614746}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.885427713394165},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.6340420246124268},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5980485677719116},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.587955117225647},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.572435200214386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5606083273887634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557995617389679},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5489552021026611},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.45854878425598145},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.45252978801727295},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.42870235443115234},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37578096985816956},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2182631492614746},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1498759.1498811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.501.3246","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.501.3246","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/~xuerui/papers/xlingual.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.567.5826","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.567.5826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wsdm2009.org/papers/p74-wang.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.7916","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.7916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.technion.ac.il/~gabr/publications/papers/Wang2009RCL.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1489959797","https://openalex.org/W1968995675","https://openalex.org/W1972640883","https://openalex.org/W1987718503","https://openalex.org/W1994966918","https://openalex.org/W2012887702","https://openalex.org/W2031685401","https://openalex.org/W2062630764","https://openalex.org/W2064885744","https://openalex.org/W2090955184","https://openalex.org/W2098249418","https://openalex.org/W2098876286","https://openalex.org/W2099031744","https://openalex.org/W2101105183","https://openalex.org/W2120708938","https://openalex.org/W2123198781","https://openalex.org/W2130903752","https://openalex.org/W2145631291","https://openalex.org/W2150749667","https://openalex.org/W2158108973","https://openalex.org/W2161477126","https://openalex.org/W3003665436","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2572349046","https://openalex.org/W2096359267","https://openalex.org/W2026738364","https://openalex.org/W3197639690","https://openalex.org/W2124814993","https://openalex.org/W2113390685","https://openalex.org/W2017989738","https://openalex.org/W1981131819","https://openalex.org/W8514837","https://openalex.org/W2186703450"],"abstract_inverted_index":{"The":[0],"non-English":[1,131],"Web":[2,118,156],"is":[3,57,61,91,109,201],"growing":[4],"at":[5,96],"phenomenal":[6],"speed,":[7],"but":[8],"available":[9,44],"language":[10,56,163],"processing":[11,79],"tools":[12],"and":[13,30,120,143,189],"resources":[14],"are":[15,19,26,41],"predominantly":[16],"English-based.":[17],"Taxonomies":[18],"a":[20,126],"case":[21],"in":[22,81,117,121,159,183],"point:":[23],"while":[24],"there":[25],"plenty":[27],"of":[28,46,167,174],"commercial":[29],"non-commercial":[31],"taxonomies":[32,37,53,68],"for":[33,38,54,111,129],"the":[34,89,113,155,160,172],"English":[35,67,135,140],"Web,":[36],"other":[39,82],"languages":[40,184],"either":[42],"not":[43],"or":[45],"arguable":[47],"quality.":[48],"Given":[49],"that":[50,88,152,198],"building":[51],"comprehensive":[52],"each":[55],"prohibitively":[58],"expensive,":[59],"it":[60],"natural":[62],"to":[63,76,95,204],"ask":[64],"whether":[65],"existing":[66,139],"can":[69,170],"be":[70],"leveraged,":[71],"possibly":[72],"via":[73],"machine":[74,145,176],"translation,":[75],"enable":[77],"text":[78,141],"tasks":[80],"languages.":[83,207],"Our":[84],"experimental":[85],"results":[86,158],"confirm":[87],"answer":[90],"affirmative":[92],"with":[93],"respect":[94],"least":[97],"one":[98],"task.":[99],"In":[100,148],"this":[101],"study":[102],"we":[103,150,169,196],"focus":[104],"on":[105,180],"query":[106,181],"classification,":[107],"which":[108],"essential":[110],"understanding":[112],"user":[114],"intent":[115],"both":[116],"search":[119,157],"online":[122],"advertising.":[123],"We":[124],"propose":[125],"robust":[127],"method":[128],"classifying":[130],"queries":[132],"into":[133],"an":[134,138],"taxonomy,":[136],"using":[137],"classifier":[142],"off-the-shelf":[144],"translation":[146],"systems.":[147],"particular,":[149],"show":[151],"by":[153],"considering":[154],"query's":[161],"original":[162],"as":[164,185,187],"additional":[165,206],"sources":[166],"information,":[168],"alleviate":[171],"effect":[173],"erroneous":[175],"translation.":[177],"Empirical":[178],"evaluation":[179],"sets":[182],"diverse":[186],"Chinese":[188],"Russian":[190],"yields":[191],"very":[192],"encouraging":[193],"results;":[194],"consequently,":[195],"believe":[197],"our":[199],"approach":[200],"also":[202],"applicable":[203],"many":[205]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}