{"id":"https://openalex.org/W4290944172","doi":"https://doi.org/10.1145/3534678.3539189","title":"Multilingual Taxonomic Web Page Classification for Contextual Targeting at Yahoo","display_name":"Multilingual Taxonomic Web Page Classification for Contextual Targeting at Yahoo","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290944172","doi":"https://doi.org/10.1145/3534678.3539189"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539189","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055552568","display_name":"Eric Ye","orcid":"https://orcid.org/0009-0003-4976-647X"},"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":"Eric Ye","raw_affiliation_strings":["Yahoo Research, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581308","display_name":"Xiao Bai","orcid":"https://orcid.org/0000-0002-7491-2454"},"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":"Xiao Bai","raw_affiliation_strings":["Yahoo Research, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061972189","display_name":"Neil O\u2019Hare","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":"Neil O'Hare","raw_affiliation_strings":["Yahoo Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015704435","display_name":"Eliyar Asgarieh","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":"Eliyar Asgarieh","raw_affiliation_strings":["Yahoo Research, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005163929","display_name":"Kapil Thadani","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":"Kapil Thadani","raw_affiliation_strings":["Yahoo Research, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, New York, NY, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011818844","display_name":"Francisco Perez-Sorrosal","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":"Francisco Perez-Sorrosal","raw_affiliation_strings":["Yahoo Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028499894","display_name":"Sujyothi Adiga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sujyothi Adiga","raw_affiliation_strings":["Yahoo, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4372","last_page":"4380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9995999932289124,"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":0.9976000189781189,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9947999715805054,"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":0.7926971912384033},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7164555788040161},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6858760714530945},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5970571041107178},{"id":"https://openalex.org/keywords/contextual-advertising","display_name":"Contextual advertising","score":0.5742826461791992},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5685620307922363},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4984760284423828},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4544607996940613},{"id":"https://openalex.org/keywords/targeted-advertising","display_name":"Targeted advertising","score":0.4493626654148102},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4191301167011261},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3892214000225067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38346993923187256},{"id":"https://openalex.org/keywords/online-advertising","display_name":"Online advertising","score":0.336390882730484},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3084888160228729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926971912384033},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7164555788040161},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6858760714530945},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5970571041107178},{"id":"https://openalex.org/C70133500","wikidata":"https://www.wikidata.org/wiki/Q1815904","display_name":"Contextual advertising","level":4,"score":0.5742826461791992},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5685620307922363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4984760284423828},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4544607996940613},{"id":"https://openalex.org/C2777459780","wikidata":"https://www.wikidata.org/wiki/Q1628411","display_name":"Targeted advertising","level":2,"score":0.4493626654148102},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4191301167011261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3892214000225067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38346993923187256},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.336390882730484},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3084888160228729},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","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},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539189","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539189","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W9981647","https://openalex.org/W2073448073","https://openalex.org/W2146241755","https://openalex.org/W2148143831","https://openalex.org/W2150766729","https://openalex.org/W2161914364","https://openalex.org/W2295598076","https://openalex.org/W2612690371","https://openalex.org/W2743289088","https://openalex.org/W2769280657","https://openalex.org/W2891555348","https://openalex.org/W2913187784","https://openalex.org/W2963026768","https://openalex.org/W2973088264","https://openalex.org/W2999962654","https://openalex.org/W3034368386","https://openalex.org/W3035390927","https://openalex.org/W3104723404","https://openalex.org/W3138154797","https://openalex.org/W3208848490","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2334894004","https://openalex.org/W4245966242","https://openalex.org/W798724878","https://openalex.org/W2147236364","https://openalex.org/W2048003064","https://openalex.org/W2547194909","https://openalex.org/W1977586106","https://openalex.org/W2147949663"],"abstract_inverted_index":{"As":[0],"we":[1,64],"move":[2],"toward":[3],"a":[4,46,151],"cookie-less":[5],"world,":[6],"the":[7,56,93,100,137,148,178,185],"ability":[8],"to":[9,41,45,55,71,85,98,122,162],"track":[10],"users'":[11],"online":[12],"activities":[13],"for":[14,27,88,114,154,181],"behavior":[15],"targeting":[16,23,32,156,183],"will":[17],"be":[18],"drastically":[19],"reduced,":[20],"making":[21],"contextual":[22,31,155,182],"an":[24],"appealing":[25],"alternative":[26],"advertising":[28],"platforms.":[29],"Category-based":[30],"displays":[33],"ads":[34],"on":[35],"web":[36,50,73,142],"pages":[37,74,143],"that":[38,110,126,158],"are":[39,112,127],"relevant":[40],"advertiser-targeted":[42],"categories,":[43,90],"according":[44],"pre-defined":[47],"taxonomy.":[48],"Accurate":[49],"page":[51],"classification":[52],"is":[53,171],"key":[54],"success":[57],"of":[58,102,131],"this":[59,62],"approach.":[60],"In":[61],"paper,":[63],"use":[65],"multilingual":[66],"Transformer-based":[67],"transfer":[68],"learning":[69],"models":[70,125,180],"classify":[72],"in":[75,129,157,184],"five":[76],"high-impact":[77],"languages.":[78],"We":[79,118,176],"adopt":[80],"multiple":[81],"data":[82],"sampling":[83],"techniques":[84],"increase":[86],"coverage":[87],"rare":[89,105],"and":[91,135,174],"modify":[92],"loss":[94],"using":[95,144],"class-based":[96],"re-weighting":[97],"smooth":[99],"influence":[101],"frequent":[103],"versus":[104],"categories.":[106],"Offline":[107],"evaluation":[108],"shows":[109],"these":[111],"crucial":[113],"improving":[115],"our":[116],"classifiers.":[117],"leverage":[119],"knowledge":[120],"distillation":[121],"train":[123],"accurate":[124],"lightweight":[128],"terms":[130],"(i)":[132],"model":[133],"size,":[134],"(ii)":[136],"input":[138],"text":[139,146],"used.":[140],"Classifying":[141],"only":[145],"from":[147],"URL":[149],"addresses":[150],"unique":[152],"challenge":[153],"bid":[159],"requests":[160],"come":[161],"ad":[163],"systems":[164],"as":[165],"URLs":[166],"without":[167],"content,":[168],"while":[169],"crawling":[170],"time":[172],"consuming":[173],"costly.":[175],"launched":[177],"proposed":[179],"Yahoo":[186],"DSP,":[187],"significantly":[188],"increasing":[189],"its":[190],"revenue.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
