{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T18:33:49Z","timestamp":1775586829095,"version":"3.50.1"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Sirindhorn International Institute of Technology"},{"name":"Thammasat University, Tokyo Institute of Technology and National Electronics and Computer Technology Center (NECTEC), Thailand"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2024,4,30]]},"abstract":"<jats:p>\n            Several methodologies have recently been proposed to enhance the performance of low-resource Neural Machine Translation (NMT). However, these techniques have yet to be explored thoroughly in the low-resource Thai and Myanmar languages. Therefore, we first applied augmentation techniques such as SwitchOut and Ciphertext Based Data Augmentation (CipherDAug) to improve NMT performance in these languages. Second, we enhanced the NMT performance by fine-tuning the pre-trained Multilingual Denoising BART model (mBART), where BART denotes Bidirectional and Auto-Regressive Transformer. We implemented three NMT systems: namely, Transformer+SwitchOut, Multi-Source Transformer+CipherDAug, and fine-tuned mBART in the bidirectional translations of Thai-English-Myanmar language pairs from the ASEAN-MT corpus. Experimental results showed that Multi-Source Transformer+CipherDAug significantly improved Bilingual Evaluation Understudy (BLEU),\n            <jats:bold>Character n-gram F-score (ChrF)<\/jats:bold>\n            , and\n            <jats:bold>Translation Error Rate (TER)<\/jats:bold>\n            scores over the first baseline Transformer and second baseline Edit-Based Transformer. The model achieved notable BLEU scores: 37.9 (English-to-Thai), 42.7 (Thai-to-English), 28.9 (English-to-Myanmar), 31.2 (Myanmar-to-English), 25.3 (Thai-to-Myanmar), and 25.5 (Myanmar-to-Thai). The fine-tuned mBART model also considerably outperformed the two baselines, except for the Myanmar-to-English pair. SwitchOut improved over the second baseline in all pairs and performed similarly to the first baseline in most cases. Last, we performed detailed analyses verifying that the CipherDAug and mBART models potentially facilitate improving low-resource NMT performance in Thai and Myanmar languages.\n          <\/jats:p>","DOI":"10.1145\/3645111","type":"journal-article","created":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:51:05Z","timestamp":1707832265000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["A Study for Enhancing Low-resource Thai-Myanmar-English Neural Machine Translation"],"prefix":"10.1145","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9078-4404","authenticated-orcid":false,"given":"Mya Ei","family":"San","sequence":"first","affiliation":[{"name":"School of ICT, Sirindhorn International Institute of Technology, Thammasat University, Khlong Nueng, Thailand"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4432-7315","authenticated-orcid":false,"given":"Sasiporn","family":"Usanavasin","sequence":"additional","affiliation":[{"name":"School of ICT, Sirindhorn International Institute of Technology, Thammasat University, Khlong Nueng, Thailand"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3115-6166","authenticated-orcid":false,"given":"Ye Kyaw","family":"Thu","sequence":"additional","affiliation":[{"name":"Language and Semantic Technology Research Team (LST), Artificial Intelligence Research Group (AINRG), National Electronics and Computer Technology Center (NECTEC), Muang, Thailand"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7730-1536","authenticated-orcid":false,"given":"Manabu","family":"Okumura","sequence":"additional","affiliation":[{"name":"Laboratory for Future Interdisciplinary Research of Science and Technology, Tokyo Institute of Technology, Meguro-ku, Japan"}]}],"member":"320","published-online":{"date-parts":[[2024,4,15]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-021-09264-2"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5213"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5203"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.263"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2090"},{"key":"e_1_3_2_7_2","article-title":"A theoretically grounded application of dropout in recurrent neural networks","volume":"29","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. A theoretically grounded application of dropout in recurrent neural networks. In Advances in Neural Information Processing Systems, Vol. 29.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2022.e10375"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wat-1.8"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6467"},{"key":"e_1_3_2_11_2","first-page":"1700","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Kalchbrenner Nal","year":"2013","unstructured":"Nal Kalchbrenner and Phil Blunsom. 2013. Recurrent continuous translation models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 1700\u20131709. https:\/\/aclanthology.org\/D13-1176"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.17"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-021-09536-6"},{"key":"e_1_3_2_16_2","volume-title":"Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation","author":"Marie Benjamin","year":"2018","unstructured":"Benjamin Marie, Atsushi Fujita, and Eiichiro Sumita. 2018. Combination of statistical and neural machine translation for Myanmar-English. In Proceedings of the 32nd Pacific Asia Conference on Language, Information and Computation: 5th Workshop on Asian Translation: 5th Workshop on Asian Translation, Stephen Politzer-Ahles, Yu-Yin Hsu, Chu-Ren Huang, and Yao Yao (Eds.). Association for Computational Linguistics."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-4007"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157290"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-4009"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.373"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w15-3049"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Matt Post. 2018. A call for clarity in reporting BLEU scores. In Proceedings of the 3rd Conference on Machine Translation: Research Papers. Association for Computational Linguistics 186\u2013191. 10.18653\/v1\/W18-6319","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_24_2","article-title":"Technical report for the network-based asean language translation public service project","author":"Prachya Boonkwan","year":"2013","unstructured":"Boonkwan Prachya and Supnithi Thepchai. 2013. Technical report for the network-based asean language translation public service project. In Online Materials of Network-based ASEAN Languages Translation Public Service for Members.","journal-title":"Online Materials of Network-based ASEAN Languages Translation Public Service for Members"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Xi Peng Qiu Tian Xiang Sun Yi Ge Xu Yun Fan Shao Ning Dai and Xuan Jing Huang. 2020. Pre-trained models for natural language processing: A survey. Sci. China Technol. Sci. 63 10 (2020) 1872\u20131897. 10.1007\/s11431-020-1647-3","DOI":"10.1007\/s11431-020-1647-3"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/iSAI-NLP54397.2021.9678159"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/iSAI-NLP56921.2022.9960261"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2209"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2323"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"e_1_3_2_31_2","first-page":"223","volume-title":"Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers","author":"Snover Matthew","year":"2006","unstructured":"Matthew Snover, Bonnie Dorr, Rich Schwartz, Linnea Micciulla, and John Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers. Association for Machine Translation in the Americas, 223\u2013231."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.304"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5209"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1100"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00368"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"e_1_3_2_38_2","unstructured":"Changtong Zan Liang Ding Li Shen Yu Cao Weifeng Liu and Dacheng Tao. 2022. Bridging cross-lingual gaps during leveraging the multilingual sequence-to-sequence pretraining for text generation and understanding. arxiv:2204.07834 [cs.CL]. Retrieved from https:\/\/arxiv.org\/abs\/2204.07834"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3645111","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3645111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:28Z","timestamp":1750291408000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3645111"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4,30]]}},"alternative-id":["10.1145\/3645111"],"URL":"https:\/\/doi.org\/10.1145\/3645111","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2023-08-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}