{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T12:11:40Z","timestamp":1779106300435,"version":"3.51.4"},"reference-count":24,"publisher":"Wiley","license":[{"start":{"date-parts":[[2020,11,29]],"date-time":"2020-11-29T00:00:00Z","timestamp":1606608000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2020,11,29]]},"abstract":"<jats:p>Building the first Russian-Vietnamese neural machine translation system, we faced the problem of choosing a translation unit system on which source and target embeddings are based. Available homogeneous translation unit systems with the same translation unit on the source and target sides do not perfectly suit the investigated language pair. To solve the problem, in this paper, we propose a novel heterogeneous translation unit system, considering linguistic characteristics of the synthetic Russian language and the analytic Vietnamese language. Specifically, we decrease the embedding level on the source side by splitting token into subtokens and increase the embedding level on the target side by merging neighboring tokens into supertoken. The experiment results show that the proposed heterogeneous system improves over the existing best homogeneous Russian-Vietnamese translation system by 1.17 BLEU. Our approach could be applied to building translation bots for language pairs with different linguistic characteristics.<\/jats:p>","DOI":"10.1155\/2020\/8859452","type":"journal-article","created":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T02:52:16Z","timestamp":1606704736000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Mixed-Level Neural Machine Translation"],"prefix":"10.1155","volume":"2020","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7796-4778","authenticated-orcid":true,"given":"Thien","family":"Nguyen","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huu","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Ho Chi Minh City University of Food Industry, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0793-9590","authenticated-orcid":true,"given":"Phuoc","family":"Tran","sequence":"additional","affiliation":[{"name":"Natural Language Processing and Knowledge Discovery Laboratory, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"J. Chung"},{"key":"2","first-page":"1724","article-title":"Learning phrase representations using rnn encoder\u2013decoder for statistical machine translation","author":"K. Cho"},{"key":"3","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"I. Sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"4","first-page":"1412","article-title":"Effective approaches to attention-based neural machine translation","author":"M.-T. Luong"},{"key":"5","first-page":"371","article-title":"Edinburgh neural machine translation systems for wmt 16","volume-title":"in","author":"R. Sennrich"},{"key":"6","first-page":"237","article-title":"Neural machine translation for morphologically rich languages with improved sub-word units and synthetic data","author":"M. Pinnis"},{"key":"7","first-page":"66","article-title":"Subword regularization: improving neural network translation models with multiple subword candidates","author":"T. Kudo"},{"key":"8","first-page":"618","article-title":"Improving neural machine translation by incorporating hierarchical subword features","author":"M. Morishita"},{"key":"9","first-page":"53","article-title":"Finding better subword segmentation for neural machine translation","author":"Y. Wu"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00067"},{"key":"11","first-page":"228","article-title":"Plan, attend, generate: character-level neural machine translation with planning","author":"C. Gulcehre"},{"key":"12","first-page":"376","article-title":"How grammatical is character-level neural machine translation? assessing mt quality with contrastive translation pairs","author":"R. Sennrich"},{"key":"13","first-page":"653","article-title":"On adversarial examples for character-level neural machine translation","author":"J. Ebrahimi"},{"key":"14","first-page":"76","article-title":"Stanford neural machine translation systems for spoken language domains","author":"M.-T. Luong"},{"key":"15","first-page":"177","article-title":"Moses: open source toolkit for statistical machine translation","author":"P. Koehn"},{"key":"16","first-page":"71","article-title":"A quantitative and typological approach to correlating linguistic complexity","author":"Y. M. Oh"},{"key":"17","first-page":"120","article-title":"Towards state-of-the-art English-Vietnamese neural machine translation","author":"H.-H. Phan-Vu"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.15625\/1813-9663\/35\/2\/13233"},{"key":"19","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"A. Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/9821608"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/2988237"},{"key":"22","first-page":"56","article-title":"Vncorenlp: a Vietnamese natural language processing toolkit,","author":"T. Vu"},{"key":"23","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"J. Devlin"},{"key":"24","first-page":"63","article-title":"Nltk: The Natural Language Toolkit","author":"E. Loper"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2020\/8859452.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2020\/8859452.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2020\/8859452.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T02:52:18Z","timestamp":1606704738000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cin\/2020\/8859452\/"}},"subtitle":[],"editor":[{"given":"Akbar S.","family":"Namin","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,11,29]]},"references-count":24,"alternative-id":["8859452","8859452"],"URL":"https:\/\/doi.org\/10.1155\/2020\/8859452","relation":{},"ISSN":["1687-5273","1687-5265"],"issn-type":[{"value":"1687-5273","type":"electronic"},{"value":"1687-5265","type":"print"}],"subject":[],"published":{"date-parts":[[2020,11,29]]}}}