{"id":"https://openalex.org/W4323338301","doi":"https://doi.org/10.1109/access.2023.3252898","title":"A Data Augmentation Method for English-Vietnamese Neural Machine Translation","display_name":"A Data Augmentation Method for English-Vietnamese Neural Machine Translation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4323338301","doi":"https://doi.org/10.1109/access.2023.3252898"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3252898","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3252898","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10058922.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10058922.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006148861","display_name":"Nghia Luan Pham","orcid":"https://orcid.org/0000-0003-3922-2607"},"institutions":[{"id":"https://openalex.org/I3132161128","display_name":"Hai Phong University","ror":"https://ror.org/0227kwk61","country_code":"VN","type":"education","lineage":["https://openalex.org/I3132161128"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Nghia Luan Pham","raw_affiliation_strings":["Library and Information Center, Hai Phong University, Haiphong, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-3922-2607","affiliations":[{"raw_affiliation_string":"Library and Information Center, Hai Phong University, Haiphong, Vietnam","institution_ids":["https://openalex.org/I3132161128"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Van Vinh Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177233841","display_name":"Vietnam National University, Hanoi","ror":"https://ror.org/02jmfj006","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van Vinh Nguyen","raw_affiliation_strings":["Faculty of Information Technology, University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Engineering and Technology, Vietnam National University, Hanoi, Vietnam","institution_ids":["https://openalex.org/I177233841"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002267927","display_name":"Thang V. Pham","orcid":"https://orcid.org/0000-0003-0333-2492"},"institutions":[{"id":"https://openalex.org/I911458345","display_name":"Amsterdam UMC Location Vrije Universiteit Amsterdam","ror":"https://ror.org/00q6h8f30","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I4210151833","https://openalex.org/I911458345"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thang Viet Pham","raw_affiliation_strings":["VU University Medical Center, Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-0333-2492","affiliations":[{"raw_affiliation_string":"VU University Medical Center, Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I911458345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006148861"],"corresponding_institution_ids":["https://openalex.org/I3132161128"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.5276,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91158787,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"28034","last_page":"28044"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/machine-translation","display_name":"Machine translation","score":0.8986256122589111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8883333206176758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6818525791168213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6635903716087341},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.607170581817627},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.582470178604126},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.579228401184082},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5746728777885437},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.49907588958740234},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4604327082633972},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.4515506327152252},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4428122639656067},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.4343823492527008},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4126034379005432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38605254888534546}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8986256122589111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8883333206176758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6818525791168213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6635903716087341},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.607170581817627},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.582470178604126},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.579228401184082},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5746728777885437},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.49907588958740234},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4604327082633972},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.4515506327152252},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4428122639656067},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.4343823492527008},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4126034379005432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38605254888534546},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":3,"locations":[{"id":"doi:10.1109/access.2023.3252898","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3252898","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10058922.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:pure.amsterdamumc.nl:publications/6e0aeeb3-5cad-49cf-a47d-f56bdd671bb5","is_oa":true,"landing_page_url":"https://pure.amsterdamumc.nl/en/publications/6e0aeeb3-5cad-49cf-a47d-f56bdd671bb5","pdf_url":"https://pure.amsterdamumc.nl/ws/files/152250943/A-data-augmentation-method-for-english-vietnamese-neural-machine-translation.pdf","source":{"id":"https://openalex.org/S7407055222","display_name":"Pure Amsterdam UMC","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pham, N L, Vinh Nguyen, V & Pham, T V 2023, 'A Data Augmentation Method for English-Vietnamese Neural Machine Translation', IEEE Access, vol. 11, pp. 28034-28044. https://doi.org/10.1109/ACCESS.2023.3252898","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:8adc80bff6d840a8b68ee527ee250616","is_oa":true,"landing_page_url":"https://doaj.org/article/8adc80bff6d840a8b68ee527ee250616","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 28034-28044 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3252898","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3252898","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10058922.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4323338301.pdf","grobid_xml":"https://content.openalex.org/works/W4323338301.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1757859293","https://openalex.org/W2009847538","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2164628107","https://openalex.org/W2194775991","https://openalex.org/W2525778437","https://openalex.org/W2561274697","https://openalex.org/W2595715041","https://openalex.org/W2756566411","https://openalex.org/W2786520898","https://openalex.org/W2805430026","https://openalex.org/W2885213066","https://openalex.org/W2888539709","https://openalex.org/W2915977493","https://openalex.org/W2962015539","https://openalex.org/W2962712961","https://openalex.org/W2963216553","https://openalex.org/W2963975242","https://openalex.org/W2964199361","https://openalex.org/W2979826702","https://openalex.org/W2987044206","https://openalex.org/W3002887707","https://openalex.org/W3038626969","https://openalex.org/W3101825254","https://openalex.org/W3119912091","https://openalex.org/W3133652505","https://openalex.org/W3193077216","https://openalex.org/W3201915713","https://openalex.org/W3211848854","https://openalex.org/W4385245566","https://openalex.org/W6605403940","https://openalex.org/W6608606290","https://openalex.org/W6637698695","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6745388339","https://openalex.org/W6769834034","https://openalex.org/W6773097386","https://openalex.org/W6783433986","https://openalex.org/W6783995010","https://openalex.org/W6801449731","https://openalex.org/W6998570333"],"related_works":["https://openalex.org/W3204448004","https://openalex.org/W2566847733","https://openalex.org/W2122287718","https://openalex.org/W2753600765","https://openalex.org/W2962780935","https://openalex.org/W193726211","https://openalex.org/W2740094425","https://openalex.org/W2587602790","https://openalex.org/W2532807140","https://openalex.org/W4378619223"],"abstract_inverted_index":{"The":[0,53,172],"translation":[1,5,115,150,159,189],"quality":[2,20,111,137],"of":[3,21,55,112,138],"machine":[4,51,158,185],"systems":[6],"depends":[7],"on":[8],"the":[9,17,22,56,110,113,136,146,161,169,176,195,205],"parallel":[10,30,41,81,122,182],"corpus":[11,31,123],"used":[12,49],"for":[13,37,134,141,164,184],"training,":[14],"in":[15,50,93,101,168],"particular":[16],"quantity":[18],"and":[19,28,34,68,75,103,166],"corpus.":[23,42],"However,":[24],"building":[25],"a":[26,38,120,132],"high-quality":[27],"large-scale":[29],"is":[32,59,63,116,198],"complex":[33],"expensive,":[35],"particularly":[36],"specific":[39],"domain":[40],"Therefore,":[43,109],"data":[44,147,183],"augmentation":[45],"techniques":[46],"are":[47],"widely":[48],"translation.":[52],"input":[54],"back-translation":[57],"method":[58,71,133,178],"monolingual":[60,85,139],"text,":[61],"which":[62,94],"available":[64],"from":[65,90,96],"many":[66],"sources,":[67,92],"therefore":[69],"this":[70,128],"can":[72,87,179],"be":[73,88],"easily":[74],"effectively":[76,180],"implemented":[77],"to":[78,119,204],"generate":[79],"synthetic":[80],"data.":[82],"In":[83,127,191],"practice,":[84],"texts":[86,140],"collected":[89],"different":[91],"sources":[95],"websites":[97],"often":[98],"have":[99],"errors":[100],"grammar":[102],"spelling,":[104],"sentence":[105],"mismatch":[106],"or":[107],"freestyle.":[108],"output":[114],"reduced,":[117],"leading":[118],"low-quality":[121],"generated":[124],"by":[125,148,200],"back-translation.":[126,142],"study,":[129],"we":[130,144],"propose":[131],"improving":[135,188],"Moreover,":[143],"supplemented":[145],"pruning":[149],"table.":[151],"We":[152],"experimented":[153],"with":[154],"an":[155],"English-Vietnamese":[156],"neural":[157],"using":[160],"IWSLT2015":[162],"dataset":[163],"training":[165],"testing":[167],"legal":[170],"domain.":[171],"results":[173],"showed":[174],"that":[175],"proposed":[177],"augment":[181],"translation,":[186],"thereby":[187],"quality.":[190],"our":[192],"experimental":[193],"cases,":[194],"BLEU":[196],"score":[197],"increased":[199],"16.37":[201],"points":[202],"compared":[203],"baseline":[206],"system.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}