{"id":"https://openalex.org/W3199323859","doi":"https://doi.org/10.21437/interspeech.2022-10177","title":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese","display_name":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3199323859","doi":"https://doi.org/10.21437/interspeech.2022-10177","mag":"3199323859"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10177","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5010886079","display_name":"Nguyen Luong Tran","orcid":"https://orcid.org/0000-0002-7373-932X"},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Nguyen Luong Tran","raw_affiliation_strings":["VinAI Research, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"VinAI Research, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079263849","display_name":"Duong Le","orcid":"https://orcid.org/0000-0002-3048-9180"},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Duong Le","raw_affiliation_strings":["VinAI Research, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"VinAI Research, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060483283","display_name":"Dat Quoc Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dat Quoc Nguyen","raw_affiliation_strings":["VinAI Research, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"VinAI Research, Hanoi, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010886079"],"corresponding_institution_ids":["https://openalex.org/I4210142044"],"apc_list":null,"apc_paid":null,"fwci":4.7813,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96148459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7570921182632446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6219946146011353},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5762171149253845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46108219027519226},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.05680638551712036},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.044296592473983765},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.04379880428314209}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7570921182632446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219946146011353},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5762171149253845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46108219027519226},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.05680638551712036},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.044296592473983765},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.04379880428314209},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10177","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10177","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1597333669","https://openalex.org/W2154652894","https://openalex.org/W2462831000","https://openalex.org/W2885185669","https://openalex.org/W2888942278","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2913129712","https://openalex.org/W2933138175","https://openalex.org/W2945260553","https://openalex.org/W2952509486","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2964121744","https://openalex.org/W2965373594","https://openalex.org/W2979826702","https://openalex.org/W2996264288","https://openalex.org/W3011161054","https://openalex.org/W3011222885","https://openalex.org/W3034999214","https://openalex.org/W3035390927","https://openalex.org/W3036120435","https://openalex.org/W3037205571","https://openalex.org/W3082274269","https://openalex.org/W3088059392","https://openalex.org/W3095073040","https://openalex.org/W3098637735","https://openalex.org/W3104453603","https://openalex.org/W3104917146","https://openalex.org/W3107826490","https://openalex.org/W3137932235","https://openalex.org/W3166192435","https://openalex.org/W3169250374","https://openalex.org/W3169483174","https://openalex.org/W3169653581","https://openalex.org/W3176724752","https://openalex.org/W3185113268","https://openalex.org/W3190941125","https://openalex.org/W3198310612","https://openalex.org/W3199824684","https://openalex.org/W3205785479","https://openalex.org/W3214298066","https://openalex.org/W4287824654","https://openalex.org/W4288089799","https://openalex.org/W4296068435","https://openalex.org/W4298857067","https://openalex.org/W4300466035","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2291461084","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W2901718966","https://openalex.org/W3042674643","https://openalex.org/W3013355527","https://openalex.org/W3022757400","https://openalex.org/W1844055093"],"abstract_inverted_index":{"We":[0],"present":[1],"BARTpho":[2,6,9,52,74,88,103,115],"with":[3,53],"two":[4,111],"versions,":[5],"syllable":[7],"and":[8,28,65,71,80,86,89,95,99,120],"word":[10],",":[11],"which":[12],"are":[13],"the":[14,25,29,33,76,82,92],"first":[15],"public":[16],"large-scale":[17],"monolingual":[18],"sequence-to-sequence":[19,34],"models":[20],"pre-trained":[21],"for":[22,43],"Vietnamese.BARTpho":[23],"uses":[24],"\"large\"":[26],"architecture":[27],"pre-training":[30],"scheme":[31],"of":[32,61,122],"denoising":[35],"autoencoder":[36],"BART,":[37],"thus":[38],"it":[39],"is":[40,104],"especially":[41],"suitable":[42],"generative":[44,123],"NLP":[45,125],"tasks.We":[46,112],"conduct":[47],"experiments":[48],"to":[49,116],"compare":[50,87],"our":[51],"its":[54],"competitor":[55],"mBART":[56,79,90,108],"on":[57,91,109],"a":[58],"downstream":[59],"task":[60],"Vietnamese":[62,93,124],"text":[63],"summarization":[64],"show":[66],"that:":[67],"in":[68],"both":[69],"automatic":[70],"human":[72],"evaluations,":[73],"outperforms":[75],"strong":[77],"baseline":[78],"improves":[81],"state-of-the-art.We":[83],"further":[84],"evaluate":[85],"capitalization":[94],"punctuation":[96],"restoration":[97],"tasks":[98],"also":[100],"find":[101],"that":[102],"more":[105],"effective":[106],"than":[107],"these":[110],"publicly":[113],"release":[114],"facilitate":[117],"future":[118],"research":[119],"applications":[121],"tasks.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}