{"id":"https://openalex.org/W4401857086","doi":"https://doi.org/10.1145/3637528.3671625","title":"Enhancing E-commerce Spelling Correction with Fine-Tuned Transformer Models","display_name":"Enhancing E-commerce Spelling Correction with Fine-Tuned Transformer Models","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401857086","doi":"https://doi.org/10.1145/3637528.3671625"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery 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/A5027895383","display_name":"Arnab Dutta","orcid":"https://orcid.org/0009-0006-4515-5294"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arnab Dutta","raw_affiliation_strings":["eBay GmbH, Dreilinden, Germany"],"affiliations":[{"raw_affiliation_string":"eBay GmbH, Dreilinden, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106708565","display_name":"Gleb Polushin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gleb Polushin","raw_affiliation_strings":["eBay GmbH, Dreilinden, Germany"],"affiliations":[{"raw_affiliation_string":"eBay GmbH, Dreilinden, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108973980","display_name":"Xiaoshuang Zhang","orcid":"https://orcid.org/0009-0007-5698-4677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoshuang Zhang","raw_affiliation_strings":["eBay Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"eBay Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110496512","display_name":"Daniel T. Stein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Stein","raw_affiliation_strings":["eBay GmbH, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"eBay GmbH, Aachen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027895383"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6586342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4928","last_page":"4938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9972000122070312,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9957000017166138,"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":0.7712312340736389},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6373815536499023},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6129456162452698},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5901089906692505},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5411256551742554},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.480227530002594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45877018570899963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4406338036060333},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.41832906007766724},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3854973316192627},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.35693421959877014},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3372431993484497},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27000027894973755},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14881625771522522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712312340736389},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6373815536499023},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6129456162452698},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5901089906692505},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5411256551742554},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.480227530002594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45877018570899963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4406338036060333},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.41832906007766724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3854973316192627},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.35693421959877014},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3372431993484497},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27000027894973755},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14881625771522522},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671625","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th 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":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2589277916","https://openalex.org/W2962739339","https://openalex.org/W2995644293","https://openalex.org/W3001434439","https://openalex.org/W3011039321","https://openalex.org/W3025357899","https://openalex.org/W3129905227"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W2395910192","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2112752961","https://openalex.org/W2128027845","https://openalex.org/W2113687551","https://openalex.org/W4386184937","https://openalex.org/W4394728283","https://openalex.org/W1493875009"],"abstract_inverted_index":{"In":[0],"the":[1,5,11,23,36,52,63,76,147,154,171,190,193],"realm":[2],"of":[3,7,14,54,87,132,173,245,277],"e-commerce,":[4],"process":[6],"search":[8,38,236,246],"stands":[9],"as":[10,123,178],"primary":[12],"point":[13],"interaction":[15],"for":[16,97,146,183],"users,":[17],"wielding":[18],"a":[19,31,101,136,199,240,264,275],"profound":[20],"influence":[21],"on":[22],"platform's":[24],"revenue":[25],"generation.":[26],"Notably,":[27,224],"spelling":[28,98],"correction":[29,99],"assumes":[30],"pivotal":[32],"role":[33],"in":[34,139,243],"shaping":[35],"user's":[37],"experience":[39],"by":[40,126,157,230],"rectifying":[41],"erroneous":[42],"query":[43],"inputs,":[44],"thus":[45],"facilitating":[46],"more":[47],"accurate":[48],"retrieval":[49],"outcomes.":[50],"Within":[51],"scope":[53],"this":[55,88],"research":[56],"paper,":[57],"our":[58,174,260],"aim":[59],"is":[60],"to":[61,85,92,143,152,198,274],"enhance":[62],"existing":[64],"state-of-the-art":[65],"discriminative":[66],"model":[67,162,175,196],"performance":[68],"with":[69,80,208,249],"generative":[70,102],"modelling":[71],"strategies":[72],"while":[73],"concurrently":[74],"addressing":[75],"engineering":[77],"concerns":[78],"associated":[79],"real-time":[81,184,206],"online":[82],"latency,":[83,158],"inherent":[84],"models":[86,96,145],"category.":[89],"We":[90,168],"endeavor":[91],"refine":[93],"LSTM-based":[94],"classification":[95],"through":[100],"fine-tuning":[103,263],"approach":[104],"hinged":[105],"upon":[106],"pre-trained":[107],"language":[108,149],"models.":[109],"Our":[110],"comprehensive":[111],"offline":[112],"assessments":[113],"have":[114,134,160,169,257],"yielded":[115],"compelling":[116],"results,":[117],"showcasing":[118],"that":[119],"transformer-based":[120],"architectures,":[121],"such":[122],"BART":[124],"(developed":[125],"Facebook)":[127],"and":[128,192,212,235,284],"T5":[129],"(a":[130],"product":[131],"Google),":[133],"achieved":[135],"4%":[137],"enhancement":[138],"F1":[140],"score":[141],"compared":[142],"baseline":[144],"English":[148],"sites.":[150],"Furthermore,":[151],"mitigate":[153],"challenges":[155],"posed":[156],"we":[159,256],"incorporated":[161],"pruning":[163],"techniques":[164],"like":[165],"no-teacher":[166],"distillation.":[167],"undertaken":[170],"deployment":[172],"(English":[176],"only)":[177],"an":[179],"A/B":[180],"test":[181],"candidate":[182],"e-commerce":[185],"traffic,":[186],"encompassing":[187],"customers":[188],"from":[189],"US":[191],"UK.":[194],"The":[195],"attest":[197],"100%":[200],"successful":[201],"request":[202],"service":[203,221],"rate":[204],"within":[205],"scenarios,":[207],"median,":[209],"90th":[210],"percentile,":[211],"99th":[213],"percentile":[214],"(p90/p99)":[215],"latencies":[216],"comfortably":[217],"falling":[218],"below":[219],"production":[220],"level":[222],"agreements.":[223],"these":[225],"achievements":[226],"are":[227],"further":[228],"reinforced":[229],"positive":[231],"customer":[232],"engagement,":[233],"transactional":[234],"page":[237,248],"metrics,":[238],"including":[239],"significant":[241],"reduction":[242],"instances":[244],"results":[247],"low":[250],"or":[251],"almost":[252],"zero":[253],"recall.":[254],"Moreover,":[255],"also":[258],"extended":[259],"efforts":[261],"into":[262],"multilingual":[265],"model,":[266],"which,":[267],"notably,":[268],"exhibits":[269],"substantial":[270],"accuracy":[271],"enhancements,":[272],"amounting":[273],"minimum":[276],"16%,":[278],"across":[279],"four":[280],"distinct":[281],"European":[282],"languages":[283],"English.":[285]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}