{"id":"https://openalex.org/W4401936715","doi":"https://doi.org/10.1145/3674829.3675060","title":"AAVE Corpus Generation and Low-Resource Dialect Machine Translation","display_name":"AAVE Corpus Generation and Low-Resource Dialect Machine Translation","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4401936715","doi":"https://doi.org/10.1145/3674829.3675060"},"language":"en","primary_location":{"id":"doi:10.1145/3674829.3675060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674829.3675060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies","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/A5076609771","display_name":"Eric Graves","orcid":"https://orcid.org/0009-0002-1153-801X"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eric Graves","raw_affiliation_strings":["Indiana University, United States of America"],"raw_orcid":"https://orcid.org/0009-0002-1153-801X","affiliations":[{"raw_affiliation_string":"Indiana University, United States of America","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093460560","display_name":"Shreyas Aswar","orcid":"https://orcid.org/0000-0001-8993-5993"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Aswar","raw_affiliation_strings":["Indiana University, USA"],"raw_orcid":"https://orcid.org/0000-0001-8993-5993","affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rujuta Desai","orcid":"https://orcid.org/0009-0002-4658-0306"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rujuta Desai","raw_affiliation_strings":["Indiana University, USA"],"raw_orcid":"https://orcid.org/0009-0002-4658-0306","affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106864019","display_name":"Srilekha Nampelli","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srilekha Nampelli","raw_affiliation_strings":["Indiana University, USA"],"raw_orcid":"https://orcid.org/0009-0007-7363-4222","affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103241458","display_name":"Sunandan Chakraborty","orcid":"https://orcid.org/0000-0002-3331-6082"},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sunandan Chakraborty","raw_affiliation_strings":["Indiana University, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3331-6082","affiliations":[{"raw_affiliation_string":"Indiana University, United States of America","institution_ids":["https://openalex.org/I592451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112375973","display_name":"Ted Hall","orcid":null},"institutions":[{"id":"https://openalex.org/I592451","display_name":"Indiana University","ror":"https://ror.org/01kg8sb98","country_code":"US","type":"education","lineage":["https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ted Hall","raw_affiliation_strings":["Indiana University, USA"],"raw_orcid":"https://orcid.org/0009-0009-6250-4910","affiliations":[{"raw_affiliation_string":"Indiana University, USA","institution_ids":["https://openalex.org/I592451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076609771"],"corresponding_institution_ids":["https://openalex.org/I592451"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11605273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9933000206947327,"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":0.7391422986984253},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6583327651023865},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.567452609539032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5597079396247864},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.49823641777038574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4953388273715973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39583027362823486},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3783491849899292},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06439080834388733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391422986984253},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6583327651023865},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.567452609539032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5597079396247864},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.49823641777038574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4953388273715973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39583027362823486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3783491849899292},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06439080834388733},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674829.3675060","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3674829.3675060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W2002169143","https://openalex.org/W2073465154","https://openalex.org/W2178195952","https://openalex.org/W2754166059","https://openalex.org/W3203011138","https://openalex.org/W4252818871","https://openalex.org/W4303856974","https://openalex.org/W6977526205"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2775554247","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2110168585","https://openalex.org/W3107474891","https://openalex.org/W2250213760","https://openalex.org/W4386247111","https://openalex.org/W4327642362","https://openalex.org/W2587014613"],"abstract_inverted_index":{"African":[0],"American":[1,30],"Vernacular":[2],"English":[3,10,31,70],"(AAVE)":[4],"is":[5,67],"a":[6,36,111,127],"dialect":[7,167,228],"of":[8,19,91,184,215,218,227],"the":[9,14,20,85,89,182,212,216,225],"language":[11,143,145,194],"spoken":[12],"in":[13,69,107],"United":[15],"States":[16],"by":[17],"members":[18],"Black":[21,51],"community.":[22],"The":[23,102,155],"stark":[24],"differences":[25],"between":[26,50,98],"AAVE":[27,92,99,115,137,205],"and":[28,53,100,116,123,126,151,162,192,206],"Standard":[29],"(SAE),":[32],"as":[33,35,93,95,222,224],"well":[34,94,223],"historically":[37],"negative":[38,86],"stigma":[39,87],"towards":[40,88],"its":[41],"use,":[42],"have":[43],"contributed":[44],"to":[45,60,65,76,82,104,133,144,181,200],"an":[46],"academic":[47],"performance":[48],"gap":[49],"students":[52],"their":[54],"non-Black":[55],"counterparts.":[56],"This":[57,208],"research":[58,109],"works":[59],"generate":[61],"educational":[62],"resources":[63,78,103],"similar":[64],"what":[66],"available":[68],"Second":[71],"Language":[72],"(ESL)":[73],"classrooms.":[74],"Exposure":[75],"these":[77,219],"has":[79],"been":[80],"shown":[81],"both":[83,119],"improve":[84],"use":[90],"facilitate":[96],"code-switching":[97],"SAE.":[101,207],"be":[105,159,174,198],"generated":[106,220],"this":[108],"are":[110],"parallel":[112,156,202],"corpora":[113,157,186,203,221],"for":[114],"SAE":[117,135],"using":[118,138,165],"professionally":[120],"translated":[121],"text":[122],"AI-generated":[124],"text,":[125],"Neural":[128],"Machine":[129],"Translation":[130],"(NMT)":[131],"model":[132,169],"translate":[134],"into":[136],"novel":[139],"network":[140,153],"architectures":[141],"used":[142,199],"translation":[146,168,179,230],"including":[147],"LSTM,":[148],"Bi-LSTM,":[149],"Attention,":[150],"Transformer":[152],"components.":[154],"will":[158,172,197],"quantitatively":[160],"reviewed":[161],"validated":[163],"before":[164],"tested":[166],"methods.":[170],"Methodology":[171],"additionally":[173],"focused":[175],"on":[176,233],"low-resource":[177],"machine":[178,229],"due":[180],"lack":[183],"large":[185,193],"containing":[187,204],"AAVE.":[188],"Both":[189],"professional":[190],"translators":[191],"model,":[195],"ChatGPT,":[196],"create":[201],"short":[209],"paper":[210],"details":[211],"preliminary":[213],"results":[214],"assessment":[217],"accuracy":[226],"models":[231],"trained":[232],"them.":[234]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
