{"id":"https://openalex.org/W4385565172","doi":"https://doi.org/10.18653/v1/2023.acl-industry.10","title":"Domain-specific transformer models for query translation","display_name":"Domain-specific transformer models for query translation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385565172","doi":"https://doi.org/10.18653/v1/2023.acl-industry.10"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-industry.10","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.acl-industry.10","pdf_url":"https://aclanthology.org/2023.acl-industry.10.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.acl-industry.10.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074886886","display_name":"Mandar Kulkarni","orcid":"https://orcid.org/0000-0002-9005-9553"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mandar Kulkarni","raw_affiliation_strings":["Flipkart Data Science"],"affiliations":[{"raw_affiliation_string":"Flipkart Data Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080735926","display_name":"Nikesh Garera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikesh Garera","raw_affiliation_strings":["Flipkart Data Science"],"affiliations":[{"raw_affiliation_string":"Flipkart Data Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018606314","display_name":"Anusua Trivedi","orcid":"https://orcid.org/0000-0002-1315-2113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anusua Trivedi","raw_affiliation_strings":["Flipkart Data Science"],"affiliations":[{"raw_affiliation_string":"Flipkart Data Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074886886"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08614423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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":0.9591000080108643,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9581999778747559,"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":0.7967507839202881},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5213212370872498},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4532904624938965},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.44087567925453186},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42827779054641724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4140457510948181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3719770312309265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967507839202881},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5213212370872498},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4532904624938965},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.44087567925453186},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42827779054641724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4140457510948181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3719770312309265},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.acl-industry.10","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.acl-industry.10","pdf_url":"https://aclanthology.org/2023.acl-industry.10.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-industry.10","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.acl-industry.10","pdf_url":"https://aclanthology.org/2023.acl-industry.10.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385565172.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2304113845","https://openalex.org/W2793486451","https://openalex.org/W2963212250","https://openalex.org/W3004477745","https://openalex.org/W3034999214","https://openalex.org/W3168030157","https://openalex.org/W4288089799","https://openalex.org/W4300112828","https://openalex.org/W4300121149","https://openalex.org/W4300665782","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2775554247","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572"],"abstract_inverted_index":{"Due":[0],"to":[1,29,35,59,65,70,74,76,111,124,128,161],"the":[2,72,78,81,86,104,125,134,139,162,166,180,202,220,241,248,251,254,267,284],"democratization":[3],"of":[4,33,48,150,250],"e-commerce,":[5],"many":[6],"product":[7],"companies":[8],"are":[9,26,157,169],"listing":[10],"their":[11],"goods":[12],"for":[13,216,243,253],"online":[14],"shopping.":[15],"For":[16],"periodic":[17],"buying":[18],"within":[19],"a":[20,36,45,96,119,175,186,192,205],"domain":[21,221],"such":[22,101],"as":[23,159,210,234,236],"Grocery,":[24],"consumers":[25],"generally":[27],"inclined":[28],"buy":[30],"certain":[31],"brands":[32],"products.Due":[34],"large":[37],"non-English":[38],"speaking":[39],"population":[40],"in":[41,133,178,289],"India,":[42],"we":[43,117,145,173,257],"observe":[44],"significant":[46],"percentage":[47],"code-mix":[49,62,237],"Hinglish":[50,91,108,238],"search":[51],"queries":[52,63,239],"e.g.,":[53],"sasta":[54],"atta.":[55],"An":[56],"intuitive":[57],"approach":[58,269],"dealing":[60],"with":[61,196,232,281],"is":[64,185,226,286],"train":[66],"an":[67,147],"encoder-decoder":[68],"model":[69,163,225,252,285],"translate":[71],"query":[73,217],"English":[75,98,233],"perform":[77],"search.":[79],"However,":[80],"problem":[82],"becomes":[83],"non-trivial":[84],"when":[85],"brand":[87,131,153,197,276],"names":[88,92,132,156],"themselves":[89],"have":[90,95],"and":[93,165,212,228,261],"possibly":[94],"literal":[97],"translation.":[99],"In":[100,114],"queries,":[102],"only":[103],"context":[105,140],"(non-brand":[106],"name)":[107],"words":[109],"needs":[110],"be":[112,230],"translated.":[113],"this":[115],"paper,":[116],"propose":[118],"simple":[120],"yet":[121],"effective":[122],"modification":[123],"transformer":[126],"training":[127,179,203],"preserve/correct":[129],"Grocery":[130,152],"output":[135],"while":[136],"selectively":[137],"translating":[138],"words.":[141],"To":[142,246],"achieve":[143],"this,":[144],"use":[146,258],"additional":[148],"dataset":[149],"popular":[151],"names.":[154,277],"Brand":[155,176,183],"added":[158],"tokens":[160],"vocabulary,":[164],"token":[167],"embeddings":[168],"randomly":[170],"initialized.":[171],"Further,":[172],"introduce":[174],"loss":[177,184,189],"translation":[181,218,271],"model.":[182],"cross":[187],"entropy":[188],"computed":[190],"using":[191,219],"denoising":[193],"auto-encoder":[194],"objective":[195],"name":[198],"data.":[199,222],"We":[200],"warm-start":[201],"from":[204],"public":[206],"pre-trained":[207],"checkpoint":[208],"(such":[209],"BART/T5)":[211],"further":[213],"adapt":[214],"it":[215],"The":[223],"proposed":[224,268],"generic":[227],"can":[229],"used":[231],"well":[235],"alleviating":[240],"need":[242],"language":[244],"detection.":[245],"reduce":[247],"latency":[249],"production":[255],"deployment,":[256],"knowledge":[259],"distillation":[260],"quantization.":[262],"Experimental":[263],"evaluation":[264],"indicates":[265],"that":[266],"improves":[270],"results":[272,280],"by":[273],"preserving/correcting":[274],"English/Hinglish":[275],"After":[278],"positive":[279],"A/B":[282],"testing,":[283],"currently":[287],"deployed":[288],"production.":[290]},"counts_by_year":[],"updated_date":"2026-01-24T23:23:39.755997","created_date":"2025-10-10T00:00:00"}