{"id":"https://openalex.org/W4401042108","doi":"https://doi.org/10.18653/v1/2024.vardial-1.17","title":"Data-Augmentation-Based Dialectal Adaptation for LLMs","display_name":"Data-Augmentation-Based Dialectal Adaptation for LLMs","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042108","doi":"https://doi.org/10.18653/v1/2024.vardial-1.17"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.vardial-1.17","pdf_url":"https://aclanthology.org/2024.vardial-1.17.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.vardial-1.17.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101827902","display_name":"Fahim Faisal","orcid":"https://orcid.org/0000-0001-9835-6299"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fahim Faisal","raw_affiliation_strings":["Department of Computer Science , George Mason University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["Department of Computer Science , George Mason University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science , George Mason University","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101827902"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.669,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74173929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9695000052452087,"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":0.9535999894142151,"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/adaptation","display_name":"Adaptation (eye)","score":0.8182132244110107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.552912712097168},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1285437047481537},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08716589212417603}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.8182132244110107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.552912712097168},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1285437047481537},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08716589212417603}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.vardial-1.17","pdf_url":"https://aclanthology.org/2024.vardial-1.17.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.vardial-1.17","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.vardial-1.17","pdf_url":"https://aclanthology.org/2024.vardial-1.17.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 Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1262899742","display_name":"Collaborative Research: RI: Small: NL(V)P: Natural Language (Variety) Processing","funder_award_id":"2125466","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4325977314","display_name":null,"funder_award_id":"16250","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5555288946","display_name":null,"funder_award_id":"1625039","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6778642760","display_name":null,"funder_award_id":"2018631","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7185756783","display_name":null,"funder_award_id":"2327143","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G841383084","display_name":null,"funder_award_id":"IIS-2327143","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309029","display_name":"George Mason University","ror":"https://ror.org/02jqj7156"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042108.pdf","grobid_xml":"https://content.openalex.org/works/W4401042108.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0],"report":[1],"presents":[2],"GMUNLP's":[3],"participation":[4],"to":[5,36,73,109,142],"the":[6,21,60,103,119,125,132,143],"Dialect-Copa":[7],"shared":[8],"task":[9,34,75],"at":[10],"VarDial":[11],"2024":[12],"(Chifu":[13],"et":[14],"al.,":[15],"2024),":[16],"which":[17],"focuses":[18],"on":[19,30,49,77],"evaluating":[20],"commonsense":[22],"reasoning":[23],"capabilities":[24],"of":[25,62,65,128,134,146],"large":[26],"language":[27,66,149],"models":[28,67],"(LLMs)":[29],"South":[31,79],"Slavic":[32,80],"micro-dialects.The":[33],"aims":[35],"assess":[37],"how":[38],"well":[39],"LLMs":[40,135],"can":[41],"handle":[42],"nonstandard":[43],"dialectal":[44,139,154],"varieties,":[45,140],"as":[46],"their":[47],"performance":[48,76,111],"standard":[50],"languages":[51],"is":[52],"already":[53],"wellestablished.We":[54],"propose":[55],"an":[56],"approach":[57],"that":[58,102],"combines":[59],"strengths":[61],"different":[63],"types":[64],"and":[68,84,94,131,153],"leverages":[69],"data":[70,105,129],"augmentation":[71,106,130],"techniques":[72,107],"improve":[74],"three":[78,115],"dialects:":[81],"Chakavian,":[82],"Cerkno,":[83],"Torlak.We":[85],"conduct":[86],"experiments":[87],"using":[88],"a":[89,95],"language-family-focused":[90],"encoder-based":[91],"model":[92,98,121],"(BERTi)":[93],"domain-agnostic":[96],"multilingual":[97],"(AYA-101).Our":[99],"results":[100],"demonstrate":[101],"proposed":[104],"lead":[108],"substantial":[110],"gains":[112],"across":[113],"all":[114],"test":[116],"datasets":[117],"in":[118,136,151],"open-source":[120],"category.This":[122],"work":[123],"highlights":[124],"practical":[126],"utility":[127],"potential":[133],"handling":[137],"non-standard":[138],"contributing":[141],"broader":[144],"goal":[145],"advancing":[147],"natural":[148],"understanding":[150],"low-resource":[152],"settings.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}