{"id":"https://openalex.org/W4401042140","doi":"https://doi.org/10.18653/v1/2024.vardial-1.22","title":"Brandeis at VarDial 2024 DSL-ML Shared Task: Multilingual Models, Simple Baselines and Data Augmentation","display_name":"Brandeis at VarDial 2024 DSL-ML Shared Task: Multilingual Models, Simple Baselines and Data Augmentation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401042140","doi":"https://doi.org/10.18653/v1/2024.vardial-1.22"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.vardial-1.22","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.22","pdf_url":"https://aclanthology.org/2024.vardial-1.22.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-1.22.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105957308","display_name":"Jonne S\u00e4lev\u00e4","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jonne S\u00e4lev\u00e4","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042294554","display_name":"Chester Palen-Michel","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chester Palen-Michel","raw_affiliation_strings":["Mitchom School of Computer Science Brandeis University"],"affiliations":[{"raw_affiliation_string":"Mitchom School of Computer Science Brandeis University","institution_ids":["https://openalex.org/I6902469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5105957308"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09700165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8666999936103821,"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":0.8666999936103821,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.7457000017166138,"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/digital-subscriber-line","display_name":"Digital subscriber line","score":0.9341238141059875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7573456168174744},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.6888863444328308},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6350834369659424},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1986173689365387},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07596322894096375}],"concepts":[{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.9341238141059875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573456168174744},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6888863444328308},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6350834369659424},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1986173689365387},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07596322894096375},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.vardial-1.22","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.22","pdf_url":"https://aclanthology.org/2024.vardial-1.22.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-1.22","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.vardial-1.22","pdf_url":"https://aclanthology.org/2024.vardial-1.22.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":[],"funders":[{"id":"https://openalex.org/F4320310134","display_name":"Brandeis University","ror":"https://ror.org/05abbep66"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401042140.pdf","grobid_xml":"https://content.openalex.org/works/W4401042140.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1622568043","https://openalex.org/W2056183469","https://openalex.org/W2055565857","https://openalex.org/W4230802329","https://openalex.org/W2151852566","https://openalex.org/W2087366038","https://openalex.org/W4299645117","https://openalex.org/W2164592990"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,29,70,77,84,96,100,105,119,122,151,160,172],"Brandeis":[4],"University":[5],"submission":[6,21],"to":[7,28,75,118],"VarDial":[8],"2024":[9],"DSL-ML":[10],"Shared":[11],"Task":[12],"on":[13,64,83,104,121,132,154],"multilabel":[14],"classification":[15],"for":[16,162,175],"discriminating":[17],"between":[18],"similar":[19],"languages.Our":[20],"consists":[22],"of":[23,42,99],"three":[24],"entries":[25],"per":[26],"language":[27,67,142],"closed":[30],"track,":[31],"where":[32],"no":[33],"additional":[34],"data":[35],"was":[36],"permitted.Our":[37],"approach":[38],"involves":[39],"a":[40,65],"set":[41,107],"simple":[43,129],"non-neural":[44,167],"baselines":[45],"using":[46],"logistic":[47],"regression,":[48],"random":[49],"forests":[50],"and":[51,138,164],"support":[52],"vector":[53],"machines.We":[54],"follow":[55],"this":[56],"by":[57,95,159],"experimenting":[58],"with":[59,147],"finetuning":[60],"multilingual":[61],"BERT,":[62],"either":[63],"single":[66],"or":[68],"all":[69,155,176],"languages":[71,116,156],"concatenated":[72],"together.In":[73],"addition":[74],"benchmarking":[76],"model":[78],"architectures":[79],"against":[80],"one":[81],"another":[82],"development":[85,106],"set,":[86,124],"we":[87,145],"perform":[88,135],"extensive":[89],"hyperparameter":[90],"tuning,":[91],"which":[92],"is":[93],"afforded":[94],"small":[97],"size":[98],"training":[101],"data.Our":[102],"experiments":[103],"suggest":[108],"that":[109,128],"finetuned":[110],"mBERT":[111],"systems":[112],"significantly":[113],"benefit":[114],"most":[115],"compared":[117],"baseline.However,":[120],"test":[123],"our":[125,166],"results":[126],"indicate":[127],"models":[130],"based":[131],"scikit-learn":[133],"can":[134],"surprisingly":[136],"well":[137],"even":[139],"outperform":[140],"pretrained":[141],"models,":[143],"as":[144,157],"see":[146],"BCMS.Our":[148],"submissions":[149],"achieve":[150],"best":[152],"performance":[153],"reported":[158],"organizers.Except":[161],"Spanish":[163],"French,":[165],"baseline":[168],"also":[169],"ranks":[170],"in":[171],"top":[173],"3":[174],"other":[177],"languages.":[178]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}