{"id":"https://openalex.org/W4399146334","doi":"https://doi.org/10.1109/tkde.2024.3406368","title":"Multilingual Taxonomic Web Page Categorization Through Ensemble Knowledge Distillation","display_name":"Multilingual Taxonomic Web Page Categorization Through Ensemble Knowledge Distillation","publication_year":2024,"publication_date":"2024-05-29","ids":{"openalex":"https://openalex.org/W4399146334","doi":"https://doi.org/10.1109/tkde.2024.3406368"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2024.3406368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2024.3406368","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/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, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0003-4976-647X","affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, 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, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7491-2454","affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, 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\u2019Hare","raw_affiliation_strings":["Yahoo Research, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-7499-7814","affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, 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, Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0009-0486-0853","affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, 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","Yahoo Research, New York, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, New York, NY, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo Research, New York, 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, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028499894","display_name":"Sujyothi Adiga","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":"Sujyothi Adiga","raw_affiliation_strings":["Yahoo Research, Mountain View, CA, USA","Yahoo Inc., Bangalore, India"],"raw_orcid":"https://orcid.org/0009-0005-0088-6723","affiliations":[{"raw_affiliation_string":"Yahoo Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo Inc., Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58822972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"11","first_page":"6614","last_page":"6627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9707000255584717,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9707000255584717,"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":0.825888991355896},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8202548027038574},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5491901636123657},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.46255579590797424},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44844067096710205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3724120259284973},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36229604482650757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.825888991355896},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8202548027038574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5491901636123657},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.46255579590797424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44844067096710205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3724120259284973},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36229604482650757}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2024.3406368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2024.3406368","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"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":54,"referenced_works":["https://openalex.org/W1436652029","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2003471189","https://openalex.org/W2008781077","https://openalex.org/W2038553416","https://openalex.org/W2059586463","https://openalex.org/W2067698488","https://openalex.org/W2073448073","https://openalex.org/W2121715962","https://openalex.org/W2129026672","https://openalex.org/W2146241755","https://openalex.org/W2148143831","https://openalex.org/W2150766729","https://openalex.org/W2295598076","https://openalex.org/W2399051749","https://openalex.org/W2599694800","https://openalex.org/W2743289088","https://openalex.org/W2769280657","https://openalex.org/W2787518933","https://openalex.org/W2896457183","https://openalex.org/W2913187784","https://openalex.org/W2948582784","https://openalex.org/W2952638691","https://openalex.org/W2963691377","https://openalex.org/W2963703197","https://openalex.org/W2965373594","https://openalex.org/W2973088264","https://openalex.org/W2975451647","https://openalex.org/W2978017171","https://openalex.org/W2999962654","https://openalex.org/W3034368386","https://openalex.org/W3035390927","https://openalex.org/W3104723404","https://openalex.org/W3120093105","https://openalex.org/W3138154797","https://openalex.org/W3208848490","https://openalex.org/W4226302796","https://openalex.org/W4290944172","https://openalex.org/W4295364049","https://openalex.org/W4385245566","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6685974025","https://openalex.org/W6728994542","https://openalex.org/W6747898760","https://openalex.org/W6748874639","https://openalex.org/W6750523955","https://openalex.org/W6751459940","https://openalex.org/W6766673545","https://openalex.org/W6767737316","https://openalex.org/W6768351586","https://openalex.org/W6768851824","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W4247875831","https://openalex.org/W42013907"],"abstract_inverted_index":{"Web":[0],"page":[1],"categorization":[2],"has":[3,11],"been":[4,12],"extensively":[5],"studied":[6],"in":[7,47,106,134,182,245],"the":[8,25,57,72,140,147,211,216,225,238,246],"literature":[9],"and":[10,21,138,166,206,257],"successfully":[13],"used":[14],"to":[15,42,49,56,128,145,170,190,252],"improve":[16],"information":[17],"retrieval,":[18],"recommendation,":[19],"personalization":[20],"ad":[22,68,255],"targeting.":[23],"With":[24],"new":[26],"industry":[27],"trend":[28],"of":[29,74,149,160,215],"not":[30],"tracking":[31],"users'":[32],"online":[33],"behavior":[34],"without":[35],"their":[36,112,117],"explicit":[37],"permission,":[38],"using":[39,110,142,157],"contextual":[40,243],"targeting":[41,244],"accurately":[43],"understand":[44],"web":[45,76,104],"pages":[46,58,105],"order":[48],"display":[50],"ads":[51],"that":[52,100],"are":[53],"topically":[54],"relevant":[55],"becomes":[59],"more":[60],"important.":[61],"This":[62],"is":[63,82],"challenging,":[64],"however,":[65],"because":[66],"an":[67,158],"request":[69],"only":[70],"contains":[71],"URL":[73,192,218],"a":[75,79,96,172,191,253],"page.":[77],"As":[78],"result,":[80],"there":[81],"very":[83],"limited":[84,120],"available":[85],"text":[86],"for":[87,131,163,203,242],"making":[88],"accurate":[89],"classifications.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94],"propose":[95,156],"unified":[97,201],"multilingual":[98],"model":[99,194,202,220],"can":[101],"seamlessly":[102],"classify":[103],"5":[107,187],"high-impact":[108],"languages":[109,188],"either":[111],"full":[113],"content":[114],"or":[115],"just":[116],"URLs":[118],"with":[119,196],"text.":[121],"We":[122,154,223],"adopt":[123],"multiple":[124],"data":[125],"sampling":[126],"techniques":[127],"increase":[129],"coverage":[130],"rare":[132,152],"categories":[133],"our":[135],"training":[136],"corpus,":[137],"modify":[139],"loss":[141],"class-based":[143],"re-weighting":[144],"smooth":[146],"influence":[148],"frequent":[150],"versus":[151],"categories.":[153],"also":[155],"ensemble":[159],"teacher":[161,173],"models":[162],"knowledge":[164,198],"distillation":[165],"explore":[167],"different":[168],"ways":[169],"create":[171],"ensemble.":[174],"Offline":[175],"evaluation":[176],"shows":[177],"at":[178,230],"least":[179,231],"2.6%":[180],"improvement":[181],"mean":[183,212,234],"average":[184,213,235],"precision":[185,214,236],"across":[186],"compared":[189],"classification":[193,219],"trained":[195],"single-teacher":[197],"distillation.":[199],"The":[200],"both":[204],"full-content":[205],"URL-only":[207],"input":[208],"further":[209],"improves":[210],"dedicated":[217],"by":[221],"0.6%.":[222],"launched":[224],"proposed":[226],"models,":[227,241],"which":[228],"achieve":[229],"37%":[232],"better":[233],"than":[237],"legacy":[239],"tree-based":[240],"Yahoo":[247],"Demand":[248],"Side":[249],"Platform,":[250],"leading":[251],"significant":[254],"delivery":[256],"revenue":[258],"increase.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}