{"id":"https://openalex.org/W3172352177","doi":"https://doi.org/10.1145/3447548.3467092","title":"Extreme Multi-label Learning for Semantic Matching in Product Search","display_name":"Extreme Multi-label Learning for Semantic Matching in Product Search","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3172352177","doi":"https://doi.org/10.1145/3447548.3467092","mag":"3172352177"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467092","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467092","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467092","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467092","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006559148","display_name":"Wei-Cheng Chang","orcid":"https://orcid.org/0000-0002-5646-9356"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei-Cheng Chang","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051353645","display_name":"Daniel Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Jiang","raw_affiliation_strings":["Amazon, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Berkeley, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023183059","display_name":"Hsiang\u2010Fu Yu","orcid":"https://orcid.org/0000-0001-5235-2962"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hsiang-Fu Yu","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029252731","display_name":"Choon Hui Teo","orcid":"https://orcid.org/0000-0002-5724-9478"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Choon Hui Teo","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101969233","display_name":"Jiong Zhang","orcid":"https://orcid.org/0000-0003-3192-3281"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiong Zhang","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017721496","display_name":"Kai Zhong","orcid":"https://orcid.org/0000-0002-9993-6954"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhong","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028381995","display_name":"Kedarnath Kolluri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kedarnath Kolluri","raw_affiliation_strings":["Amazon, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Berkeley, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054406315","display_name":"Qie Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qie Hu","raw_affiliation_strings":["Amazon, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014007748","display_name":"Nikhil Shandilya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Shandilya","raw_affiliation_strings":["Amazon, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Berkeley, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037039757","display_name":"Vyacheslav Ievgrafov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vyacheslav Ievgrafov","raw_affiliation_strings":["Amazon, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Berkeley, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006927050","display_name":"Japinder Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Japinder Singh","raw_affiliation_strings":["Amazon, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Berkeley, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Inderjit S. Dhillon","raw_affiliation_strings":["Amazon, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon, Berkeley, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5006559148"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":7.5456,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.97692215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2643","last_page":"2651"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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/T11550","display_name":"Text and Document Classification Technologies","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9951000213623047,"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/T10028","display_name":"Topic Modeling","score":0.9948999881744385,"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":0.8108340501785278},{"id":"https://openalex.org/keywords/semantic-search","display_name":"Semantic search","score":0.5346264839172363},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5080668926239014},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4553632140159607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45406243205070496},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44541457295417786},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4425833225250244},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4412238895893097},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40733158588409424},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38015472888946533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32483774423599243},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2604401111602783}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108340501785278},{"id":"https://openalex.org/C166423231","wikidata":"https://www.wikidata.org/wiki/Q1891170","display_name":"Semantic search","level":3,"score":0.5346264839172363},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5080668926239014},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4553632140159607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45406243205070496},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44541457295417786},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4425833225250244},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4412238895893097},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40733158588409424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38015472888946533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32483774423599243},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2604401111602783},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467092","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467092","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467092","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3447548.3467092","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3447548.3467092","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3447548.3467092","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3172352177.pdf","grobid_xml":"https://content.openalex.org/works/W3172352177.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W145388748","https://openalex.org/W398859631","https://openalex.org/W1532325895","https://openalex.org/W1790954942","https://openalex.org/W2014415866","https://openalex.org/W2070996757","https://openalex.org/W2112006025","https://openalex.org/W2136189984","https://openalex.org/W2194775991","https://openalex.org/W2461743311","https://openalex.org/W2512971201","https://openalex.org/W2520348554","https://openalex.org/W2626778328","https://openalex.org/W2743021690","https://openalex.org/W2744136723","https://openalex.org/W2788125153","https://openalex.org/W2890394457","https://openalex.org/W2890634844","https://openalex.org/W2896214533","https://openalex.org/W2896457183","https://openalex.org/W2906963924","https://openalex.org/W2951434086","https://openalex.org/W2951534261","https://openalex.org/W2955665313","https://openalex.org/W2962985038","https://openalex.org/W2963469388","https://openalex.org/W2963626623","https://openalex.org/W2964369530","https://openalex.org/W2970574105","https://openalex.org/W2972801466","https://openalex.org/W2979826702","https://openalex.org/W2999508688","https://openalex.org/W3001645704","https://openalex.org/W3005296017","https://openalex.org/W3007672467","https://openalex.org/W3023045848","https://openalex.org/W3034696692","https://openalex.org/W3037422790","https://openalex.org/W3038572442","https://openalex.org/W3081146346","https://openalex.org/W3102124616","https://openalex.org/W3120689745","https://openalex.org/W3127901963","https://openalex.org/W3177232285","https://openalex.org/W4213009331","https://openalex.org/W4251326898","https://openalex.org/W4252076394","https://openalex.org/W6602019454"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2037549926","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"We":[0,152],"consider":[1,153],"the":[2,89,148,231],"problem":[3],"of":[4,23,30,150,171,181],"semantic":[5,38,82,133],"matching":[6,39,55],"in":[7,147],"product":[8,103,134,224],"search:":[9],"given":[10],"a":[11,20,168,178,188],"customer":[12,85,116],"query,":[13],"retrieve":[14,217],"all":[15],"semantically":[16],"related":[17],"products":[18,122,218],"from":[19,84],"huge":[21],"catalog":[22,32],"size":[24],"100":[25],"million,":[26],"or":[27],"more.":[28],"Because":[29],"large":[31],"spaces":[33],"and":[34,75,121,176,227],"real-time":[35,162],"latency":[36,100,170],"constraints,":[37],"algorithms":[40],"not":[41],"only":[42],"desire":[43],"high":[44],"recall":[45],"but":[46,67,88],"also":[47],"need":[48],"to":[49,62,69,99,131,197,222,230],"have":[50],"low":[51,169],"latency.":[52],"Conventional":[53],"lexical":[54],"approaches":[56],"(e.g.,":[57],"Okapi-BM25)":[58],"exploit":[59],"inverted":[60],"indices":[61],"achieve":[63],"fast":[64,161],"inference":[65,142],"time,":[66],"fail":[68],"capture":[70],"behavioral":[71],"signals":[72],"between":[73],"queries":[74,117],"products.":[76,151],"In":[77,126],"contrast,":[78],"embedding-based":[79,190],"models":[80,140,156],"learn":[81],"representations":[83],"behavior":[86],"data,":[87],"performance":[90],"is":[91,145,195],"often":[92],"limited":[93],"by":[94,136],"shallow":[95],"neural":[96],"encoders":[97],"due":[98],"constraints.":[101],"Semantic":[102],"search":[104,135,225],"can":[105,204,216],"be":[106],"viewed":[107],"as":[108],"an":[109],"eXtreme":[110],"Multi-label":[111],"Classification":[112],"(XMC)":[113],"problem,":[114],"where":[115,141],"are":[118,123,220],"input":[119],"instances":[120],"output":[124],"labels.":[125],"this":[127],"paper,":[128],"we":[129],"aim":[130],"improve":[132],"using":[137],"tree-based":[138],"XMC":[139],"time":[143],"complexity":[144],"logarithmic":[146],"number":[149],"hierarchical":[154],"linear":[155],"with":[157,200],"n-gram":[158],"features":[159],"for":[160,210],"inference.":[163],"Quantitatively,":[164],"our":[165,214],"method":[166,215],"maintains":[167],"1.25":[172],"milliseconds":[173],"per":[174],"query":[175],"achieves":[177],"65%":[179],"improvement":[180],"[email":[182],"protected]":[183],"(60.9%":[184],"v.s.":[185],"36.8%)":[186],"over":[187],"competing":[189],"DSSM":[191],"model.":[192],"Our":[193],"model":[194],"robust":[196],"weight":[198],"pruning":[199],"varying":[201],"thresholds,":[202],"which":[203],"flexibly":[205],"meet":[206],"different":[207],"system":[208,226],"requirements":[209],"online":[211],"deployments.":[212],"Qualitatively,":[213],"that":[219],"complementary":[221],"existing":[223],"add":[228],"diversity":[229],"match":[232],"set.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}