{"id":"https://openalex.org/W4205399841","doi":"https://doi.org/10.1145/3493700.3493722","title":"Enhanced Text Classification using Proxy Labels and Knowledge Distillation","display_name":"Enhanced Text Classification using Proxy Labels and Knowledge Distillation","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4205399841","doi":"https://doi.org/10.1145/3493700.3493722"},"language":"en","primary_location":{"id":"doi:10.1145/3493700.3493722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","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/A5109483976","display_name":"Rohan Sukumaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Sukumaran","raw_affiliation_strings":["PathCheck Foundation, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PathCheck Foundation, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046306364","display_name":"Sumanth Prabhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumanth Prabhu","raw_affiliation_strings":["Applied Research, Swiggy, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Research, Swiggy, IN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017720802","display_name":"Hemant Misra","orcid":"https://orcid.org/0000-0002-8179-4441"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hemant Misra","raw_affiliation_strings":["Applied Research, Swiggy, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Research, Swiggy, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2775,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60292526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.7412127256393433},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.5936753153800964},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.5730849504470825},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.506548285484314},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.505134642124176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3817209005355835},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34143730998039246},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33015310764312744},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20132067799568176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412127256393433},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.5936753153800964},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5730849504470825},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.506548285484314},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.505134642124176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817209005355835},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34143730998039246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33015310764312744},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20132067799568176},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3493700.3493722","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1999050633","https://openalex.org/W2048679005","https://openalex.org/W2090805977","https://openalex.org/W2092970348","https://openalex.org/W2101210369","https://openalex.org/W2116261113","https://openalex.org/W2133556223","https://openalex.org/W2148199310","https://openalex.org/W2163568299","https://openalex.org/W2321588627","https://openalex.org/W2769041395","https://openalex.org/W2778716599","https://openalex.org/W2959716049","https://openalex.org/W2963323070","https://openalex.org/W2963748441","https://openalex.org/W2980282514","https://openalex.org/W3034588688","https://openalex.org/W3038012435","https://openalex.org/W3177265267","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W4230315250","https://openalex.org/W2086519370","https://openalex.org/W2087343574"],"abstract_inverted_index":{"Text":[0],"Classification":[1],"has":[2],"a":[3,26,31,50,65,97,108,114,136,159,175],"variety":[4],"of":[5],"applications":[6],"in":[7,48,178,189],"the":[8,40,71,75,126,131,142,152,166,195],"pickup":[9],"and":[10,28,43,81,90,122,144,191,201],"delivery":[11],"services":[12],"industry":[13],"where":[14,100],"customers":[15],"require":[16],"one":[17],"or":[18],"more":[19],"items":[20],"to":[21,30,73,77,86,107],"be":[22,78,87,105],"picked":[23,79],"up":[24,80],"from":[25],"location":[27],"delivered":[29],"certain":[32],"destination.":[33],"Categorizing":[34],"these":[35],"customer":[36,55,72,102,196,202],"transactions":[37],"helps":[38],"understand":[39,194],"market":[41],"needs":[42],"trends":[44],"while":[45],"also":[46],"assisting":[47],"building":[49],"personalized":[51],"experience":[52],"for":[53],"each":[54,60,101],"segment.":[56],"In":[57],"this":[58],"paper,":[59],"transaction":[61,103,116,127],"is":[62,186,192],"accompanied":[63],"by":[64,70,130],"free":[66],"text":[67],"description":[68],"provided":[69,129],"describe":[74],"products":[76],"delivered.":[82],"These":[83],"descriptions":[84,128],"tend":[85],"short,":[88],"incoherent":[89],"code-mixed":[91],"(Hindi-English)":[92],"text.Here,":[93],"we":[94,155],"focus":[95],"on":[96,120,158],"specific":[98],"use-case":[99],"can":[104],"mapped":[106],"single":[109],"product":[110,199],"category.":[111],"We":[112,133,169],"propose":[113],"cost-effective":[115],"classification":[117],"approach":[118],"based":[119],"proxy-labelling":[121],"knowledge":[123],"distillation":[124],"using":[125],"customer.":[132],"introduce":[134],"R-ALBERT,":[135],"model":[137,173,185],"trained":[138],"with":[139,180],"RoBERTa":[140],"as":[141,151,163,165],"\u201cteacher\u201d":[143],"ALBERT":[145],"(33x":[146],"fewer":[147,182],"parameters":[148],"than":[149],"RoBERTa)":[150],"\u201cstudent\u201d.":[153],"Further,":[154],"benchmark":[156],"R-ALBERT":[157],"large":[160],"internal":[161],"dataset":[162],"well":[164],"20Newsgroup":[167],"dataset.":[168],"see":[170],"that":[171],"our":[172],"shows":[174],"2%":[176],"increase":[177],"performance":[179],"33x":[181],"parameters.":[183],"The":[184],"currently":[187],"deployed":[188],"production":[190],"helping":[193],"behaviour":[197],"across":[198],"categories":[200],"segments.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}