{"id":"https://openalex.org/W4400529193","doi":"https://doi.org/10.1145/3626772.3661373","title":"Embedding Based Deduplication in E-commerce AutoComplete","display_name":"Embedding Based Deduplication in E-commerce AutoComplete","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400529193","doi":"https://doi.org/10.1145/3626772.3661373"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3661373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3661373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5103326412","display_name":"S Zhai","orcid":"https://orcid.org/0009-0001-5583-0082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaodan Zhai","raw_affiliation_strings":["Coupang Inc., Mountain View, CA, USA"],"raw_orcid":"https://orcid.org/0009-0001-5583-0082","affiliations":[{"raw_affiliation_string":"Coupang Inc., Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325642","display_name":"Yuwei Chen","orcid":"https://orcid.org/0009-0004-9377-7333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuwei Chen","raw_affiliation_strings":["Coupang Inc., Mountain View, USA"],"raw_orcid":"https://orcid.org/0009-0004-9377-7333","affiliations":[{"raw_affiliation_string":"Coupang Inc., Mountain View, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032736205","display_name":"Y. Li","orcid":"https://orcid.org/0009-0000-2598-5916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixue Li","raw_affiliation_strings":["Coupang Inc., Mountain View, USA"],"raw_orcid":"https://orcid.org/0009-0000-2598-5916","affiliations":[{"raw_affiliation_string":"Coupang Inc., Mountain View, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2955","last_page":"2959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11614","display_name":"Cloud Data Security Solutions","score":0.9886999726295471,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9886999726295471,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9732000231742859,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/data-deduplication","display_name":"Data deduplication","score":0.8578948974609375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6876363754272461},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6175862550735474},{"id":"https://openalex.org/keywords/e-commerce","display_name":"E-commerce","score":0.5260369777679443},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3484242856502533},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3250998556613922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18508043885231018}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8578948974609375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876363754272461},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6175862550735474},{"id":"https://openalex.org/C78597825","wikidata":"https://www.wikidata.org/wiki/Q484847","display_name":"E-commerce","level":2,"score":0.5260369777679443},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3484242856502533},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3250998556613922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18508043885231018}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3661373","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3661373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2133845638","https://openalex.org/W2139527693","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2966372459","https://openalex.org/W2970641574","https://openalex.org/W2983415257","https://openalex.org/W3046375318","https://openalex.org/W3093334098","https://openalex.org/W4205400596","https://openalex.org/W4248414713","https://openalex.org/W4306317267","https://openalex.org/W4327811112","https://openalex.org/W4367310709","https://openalex.org/W4385958209","https://openalex.org/W6677602235","https://openalex.org/W6795383682","https://openalex.org/W6843205711"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W2943088381","https://openalex.org/W4385804830","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W4296125805"],"abstract_inverted_index":{"Query":[0],"AutoComplete":[1],"(QAC)":[2],"is":[3],"an":[4],"important":[5],"feature":[6],"in":[7,41,135,146],"e-commerce":[8,46,125,149],"search":[9,126],"engines,":[10],"aimed":[11],"at":[12,72],"enhancing":[13],"user":[14,31],"experience":[15],"by":[16],"offering":[17,139],"relevant":[18],"query":[19,42,52,93],"suggestions.":[20],"However,":[21],"these":[22],"suggestions":[23,137],"often":[24],"include":[25],"semantically":[26],"duplicate":[27],"entries":[28],"derived":[29],"from":[30],"logs.":[32],"While":[33],"the":[34,48,100,115,124,129],"existing":[35,92],"literature":[36],"has":[37,54],"made":[38],"significant":[39,116],"progress":[40],"similarity":[43,94],"learning":[44],"for":[45,69],"applications,":[47],"specific":[49],"challenge":[50],"of":[51,102,118,131],"deduplication":[53,71,81,120],"received":[55],"less":[56],"attention.":[57],"To":[58],"address":[59],"this":[60,62,88],"issue,":[61],"paper":[63],"presents":[64],"a":[65,140,147],"new":[66],"industry-scale":[67],"framework":[68,121],"QAC":[70,136],"Coupang,":[73],"utilizing":[74],"diverse":[75],"data":[76,107],"augmentation":[77,108],"techniques":[78],"to":[79],"enhance":[80],"accuracy":[82],"effectively.":[83],"Our":[84],"results":[85],"reveal":[86],"that":[87],"approach":[89],"substantially":[90],"outperforms":[91],"methods,":[95],"providing":[96],"valuable":[97],"insights":[98],"into":[99],"utility":[101],"various":[103],"pre-trained":[104],"models":[105],"and":[106,138],"strategies.":[109],"Online":[110],"A/B":[111],"testing":[112],"further":[113],"validates":[114],"impact":[117],"our":[119],"on":[122],"improving":[123],"experience,":[127],"highlighting":[128],"importance":[130],"addressing":[132],"semantic":[133],"duplicates":[134],"practical":[141],"solution":[142],"with":[143],"proven":[144],"effectiveness":[145],"live":[148],"environment.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
