{"id":"https://openalex.org/W4327979119","doi":"https://doi.org/10.1080/24751839.2023.2186625","title":"On the scalability of data augmentation techniques for low-resource machine translation between Chinese and Vietnamese","display_name":"On the scalability of data augmentation techniques for low-resource machine translation between Chinese and Vietnamese","publication_year":2023,"publication_date":"2023-03-19","ids":{"openalex":"https://openalex.org/W4327979119","doi":"https://doi.org/10.1080/24751839.2023.2186625"},"language":"en","primary_location":{"id":"doi:10.1080/24751839.2023.2186625","is_oa":true,"landing_page_url":"https://doi.org/10.1080/24751839.2023.2186625","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/24751839.2023.2186625?download=true","source":{"id":"https://openalex.org/S4210226961","display_name":"Journal of Information and Telecommunication","issn_l":"2475-1839","issn":["2475-1839","2475-1847"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information and Telecommunication","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/24751839.2023.2186625?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037002951","display_name":"Huan Vu","orcid":"https://orcid.org/0000-0002-0785-6907"},"institutions":[{"id":"https://openalex.org/I4210093659","display_name":"University of Transport and Communications","ror":"https://ror.org/006qk6d61","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210093659"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huan Vu","raw_affiliation_strings":["Faculty of Information Technology, University of Transport and Communications, Dong Da, Ha Noi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Transport and Communications, Dong Da, Ha Noi, Viet Nam","institution_ids":["https://openalex.org/I4210093659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080352912","display_name":"Ngoc Dung Bui","orcid":"https://orcid.org/0000-0001-9934-7474"},"institutions":[{"id":"https://openalex.org/I4210093659","display_name":"University of Transport and Communications","ror":"https://ror.org/006qk6d61","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210093659"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Ngoc Dung Bui","raw_affiliation_strings":["Faculty of Information Technology, University of Transport and Communications, Dong Da, Ha Noi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Transport and Communications, Dong Da, Ha Noi, Viet Nam","institution_ids":["https://openalex.org/I4210093659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080352912"],"corresponding_institution_ids":["https://openalex.org/I4210093659"],"apc_list":{"value":925,"currency":"GBP","value_usd":1134},"apc_paid":{"value":925,"currency":"GBP","value_usd":1134},"fwci":0.3537,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63345744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"7","issue":"2","first_page":"241","last_page":"253"},"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9904999732971191,"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":0.8221337795257568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.808198094367981},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6322959065437317},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5796672105789185},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5451783537864685},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5353538990020752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.525769054889679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5240723490715027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5166395306587219},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5114990472793579},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.49953436851501465},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4621719717979431},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43904775381088257},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12034520506858826},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09963655471801758},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07696378231048584},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.0669029951095581}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8221337795257568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.808198094367981},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6322959065437317},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5796672105789185},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5451783537864685},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5353538990020752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525769054889679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5240723490715027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5166395306587219},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5114990472793579},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.49953436851501465},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4621719717979431},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43904775381088257},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12034520506858826},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09963655471801758},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07696378231048584},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0669029951095581},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/24751839.2023.2186625","is_oa":true,"landing_page_url":"https://doi.org/10.1080/24751839.2023.2186625","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/24751839.2023.2186625?download=true","source":{"id":"https://openalex.org/S4210226961","display_name":"Journal of Information and Telecommunication","issn_l":"2475-1839","issn":["2475-1839","2475-1847"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information and Telecommunication","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:878d705c2e43446785b8d59fcbfad13d","is_oa":true,"landing_page_url":"https://doaj.org/article/878d705c2e43446785b8d59fcbfad13d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Information and Telecommunication, Vol 7, Iss 2, Pp 241-253 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1080/24751839.2023.2186625","is_oa":true,"landing_page_url":"https://doi.org/10.1080/24751839.2023.2186625","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/24751839.2023.2186625?download=true","source":{"id":"https://openalex.org/S4210226961","display_name":"Journal of Information and Telecommunication","issn_l":"2475-1839","issn":["2475-1839","2475-1847"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information and Telecommunication","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328589","display_name":"Tr\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc Giao th\u00f4ng v\u1eadn t\u1ea3i","ror":"https://ror.org/006qk6d61"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4327979119.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2067474758","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2164948578","https://openalex.org/W2186777530","https://openalex.org/W2461074834","https://openalex.org/W2561274697","https://openalex.org/W2612690371","https://openalex.org/W2886095922","https://openalex.org/W2888808532","https://openalex.org/W2889326796","https://openalex.org/W2912500072","https://openalex.org/W2962784628","https://openalex.org/W2963216553","https://openalex.org/W2963532001","https://openalex.org/W2970015022","https://openalex.org/W3040449765","https://openalex.org/W3170740203","https://openalex.org/W4205167092","https://openalex.org/W4241645538","https://openalex.org/W6737778391"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W2901718966","https://openalex.org/W3042674643","https://openalex.org/W3022757400","https://openalex.org/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222","https://openalex.org/W2973218968"],"abstract_inverted_index":{"Neural":[0],"Machine":[1],"Translation":[2],"(NMT)":[3],"has":[4],"constantly":[5],"been":[6,31],"shown":[7],"to":[8,13,34,54,72,76,124],"be":[9],"a":[10,15,74,92,109],"standard":[11],"choice":[12],"build":[14],"translation":[16,68],"system,":[17],"in":[18,40,65,91],"both":[19],"academia":[20],"and":[21,88],"industry.":[22],"For":[23],"low-resource":[24],"language":[25,95],"pairs,":[26],"data":[27,37,107,127],"augmentation":[28],"techniques":[29],"have":[30],"widely":[32],"used":[33],"tackle":[35],"the":[36,47,55,62,66,77,102,126],"shortage":[38],"problem":[39],"NMT.":[41],"In":[42,116],"this":[43],"paper,":[44],"we":[45,70],"investigate":[46],"scaling":[48],"behaviour":[49],"of":[50,58,79,105],"transformer-based":[51],"NMT":[52,114],"model":[53],"increasing":[56],"amount":[57,104],"synthetic":[59,106],"data.":[60],"Through":[61],"experiments,":[63],"conducted":[64],"Chinese-to-Vietnamese":[67],"task,":[69],"aim":[71],"provide":[73],"guideline":[75],"application":[78],"several":[80],"methods":[81],"such":[82],"as":[83],"back-translation,":[84,86],"tagged":[85],"self-training":[87],"sentence":[89],"concatenation":[90],"low-resource,":[93],"less-related":[94],"pair.":[96],"Our":[97],"results":[98],"suggest":[99],"that":[100],"choosing":[101],"appropriate":[103],"is":[108,122],"crucial":[110],"task":[111],"when":[112,118],"building":[113],"systems.":[115],"addition,":[117],"combining":[119],"methods,":[120],"it":[121],"recommended":[123],"tag":[125],"sources":[128],"before":[129],"training.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}
