{"id":"https://openalex.org/W4310113624","doi":"https://doi.org/10.1145/3568562.3568646","title":"Improving Khmer-Vietnamese Machine Translation with Data Augmentation methods","display_name":"Improving Khmer-Vietnamese Machine Translation with Data Augmentation methods","publication_year":2022,"publication_date":"2022-11-29","ids":{"openalex":"https://openalex.org/W4310113624","doi":"https://doi.org/10.1145/3568562.3568646"},"language":"en","primary_location":{"id":"doi:10.1145/3568562.3568646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568562.3568646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 11th International Symposium on Information and Communication Technology","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/A5031520795","display_name":"Hanh Pham Van","orcid":"https://orcid.org/0000-0001-5003-9075"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Hanh Pham Van","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0001-5003-9075","affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049610939","display_name":"L\u00ea Thanh H\u01b0\u01a1ng","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huong Le Thanh","raw_affiliation_strings":["School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0002-7628-4674","affiliations":[{"raw_affiliation_string":"School of Information and Communication Technology, Hanoi University of Science and Technology, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031520795"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.6937,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75803721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"282"},"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":0.993399977684021,"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/vietnamese","display_name":"Vietnamese","score":0.9099016189575195},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.87682044506073},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8568984270095825},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6844325661659241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.660128116607666},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6587933897972107},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5247792601585388},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4972675144672394},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4966462254524231},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4942479431629181},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4303533136844635},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4297051429748535},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4258880615234375},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13267436623573303},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08681952953338623}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.9099016189575195},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.87682044506073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568984270095825},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6844325661659241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660128116607666},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6587933897972107},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5247792601585388},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4972675144672394},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4966462254524231},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4942479431629181},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4303533136844635},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4297051429748535},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4258880615234375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13267436623573303},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08681952953338623},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":1,"locations":[{"id":"doi:10.1145/3568562.3568646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568562.3568646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 11th International Symposium on Information and Communication Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2101105183","https://openalex.org/W2153653739","https://openalex.org/W2550821151","https://openalex.org/W2800004246","https://openalex.org/W2889326796","https://openalex.org/W2900267584","https://openalex.org/W2902689991","https://openalex.org/W2902918014","https://openalex.org/W2963088995","https://openalex.org/W2963216553","https://openalex.org/W2963366389","https://openalex.org/W2964199361","https://openalex.org/W3001434439","https://openalex.org/W3036120435","https://openalex.org/W3046368065","https://openalex.org/W3093871477","https://openalex.org/W3100806282","https://openalex.org/W4226336813","https://openalex.org/W4285077564","https://openalex.org/W4285296929","https://openalex.org/W4297734170","https://openalex.org/W4299816210"],"related_works":["https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W4287644835","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W3092281475"],"abstract_inverted_index":{"Machine":[0],"translation":[1],"has":[2],"achieved":[3],"significant":[4],"improvements":[5],"with":[6,42,62],"the":[7,63,66,73,77,90,107],"development":[8],"of":[9,115],"neural":[10],"models.":[11],"However,":[12],"such":[13],"approaches":[14],"require":[15],"large-scale":[16],"parallel":[17],"data,":[18,58],"which":[19],"are":[20],"hard":[21],"to":[22,54,76,89],"collect":[23],"for":[24],"low-resource":[25,44],"language":[26,75],"pairs.":[27,119],"This":[28],"paper":[29],"solves":[30],"this":[31],"problem":[32],"by":[33],"applying":[34],"a":[35,43,81,112],"pretrained":[36],"multilingual":[37],"model":[38,110],"and":[39],"fine-tuning":[40],"it":[41],"bilingual":[45],"dataset.":[46],"In":[47],"addition,":[48],"we":[49],"propose":[50],"two":[51],"data-augmentation":[52],"strategies":[53],"receive":[55],"new":[56],"training":[57],"including:":[59],"(i)":[60],"back-translating":[61],"dataset":[64],"from":[65,72],"source":[67,74],"language;":[68],"(ii)":[69],"translating":[70],"sentences":[71],"target":[78],"one":[79],"through":[80],"pivot":[82],"language.":[83],"The":[84],"proposed":[85,99],"approach":[86,100],"is":[87],"applied":[88],"Khmer-Vietnamese":[91,117],"machine":[92],"translation.":[93],"Experimental":[94],"results":[95],"show":[96],"that":[97],"our":[98],"gains":[101],"4.426%":[102],"BLEU":[103],"score":[104],"higher":[105],"than":[106],"Google":[108],"translator":[109],"using":[111],"test":[113],"set":[114],"2000":[116],"sentence":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
