{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T10:26:01Z","timestamp":1784543161729,"version":"3.55.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"vor","delay-in-days":15,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100020912","name":"King Faisal University","doi-asserted-by":"publisher","award":["KFU253623"],"award-info":[{"award-number":["KFU253623"]}],"id":[{"id":"10.13039\/501100020912","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-33794-x","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:47:16Z","timestamp":1768319236000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Cross-lingual sparse-MoE distillation for efficient low-resource assamese\u2013english and bodo\u2013english translation"],"prefix":"10.1038","volume":"16","author":[{"given":"Basab","family":"Nath","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonis","family":"Gulzar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"33794_CR1","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y. et al. Multilingual Denoising Pre-Training for Neural Machine Translation. Transactions of the Association for Computational Linguistics 8, 726\u2013742. https:\/\/doi.org\/10.1162\/tacl_a_00343 (2020).","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"33794_CR2","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1162\/tacl_a_00453","volume":"10","author":"G Ramesh","year":"2022","unstructured":"Ramesh, G. et al. Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages. Transactions of the Association for Computational Linguistics 10, 145\u2013162. https:\/\/doi.org\/10.1162\/tacl_a_00453 (2022).","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"33794_CR3","unstructured":"Gala, J. et al. Indictrans2: Towards high-quality and accessible machine translation models for all 22 scheduled indian languages. arXiv preprint arXiv:2305.16307 (2023)."},{"key":"33794_CR4","unstructured":"Hinton, G., Vinyals, O., Dean, J. Distilling the knowledge in a neural network. NIPS Deep Learning and Representation Learning Workshop (2015)."},{"key":"33794_CR5","unstructured":"Shazeer, N. et al. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In International Conference on Learning Representations (ICLR) (2017)."},{"key":"33794_CR6","unstructured":"Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems, vol.\u00a030 (2017)."},{"key":"33794_CR7","unstructured":"Song, K., Tan, X., Qin, T., Lu, J. & Liu, T.-Y. Mass: Masked sequence to sequence pre-training for language generation. International Conference on Machine Learning (ICML) (2019)."},{"key":"33794_CR8","doi-asserted-by":"publisher","first-page":"30014","DOI":"10.1038\/s41598-025-14177-8","volume":"15","author":"SMU Qumar","year":"2025","unstructured":"Qumar, S. M. U. et al. Deep Neural Architectures for Kashmiri-English Machine Translation. Scientific Reports 15, 30014. https:\/\/doi.org\/10.1038\/s41598-025-14177-8 (2025).","journal-title":"Scientific Reports"},{"key":"33794_CR9","unstructured":"Masica, C.\u00a0P. The Indo-Aryan Languages (Cambridge University Press, 1991)."},{"key":"33794_CR10","unstructured":"DeLancey, S. The Tibeto-Burman Languages. In Thurgood, G. & LaPolla, R.\u00a0J. (eds.) The Sino-Tibetan Languages, 1\u201322 (Routledge, 2012)."},{"key":"33794_CR11","doi-asserted-by":"publisher","unstructured":"Nath, B., Tamang, S., Elwasila, O. & Gulzar, Y. Task-Oriented Evaluation of Assamese Tokenizers Using Sentiment Classification. International Journal of Advanced Computer Science and Applications (IJACSA) 16, https:\/\/doi.org\/10.14569\/IJACSA.2025.0160979 (2025).","DOI":"10.14569\/IJACSA.2025.0160979"},{"key":"33794_CR12","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1017\/nlp.2024.20","volume":"31","author":"B Nath","year":"2025","unstructured":"Nath, B., Sarkar, S., Mukhopadhyay, S. & Roy, A. Improving neural machine translation by integrating transliteration for low-resource english-assamese language. Natural Language Processing 31, 306\u2013327. https:\/\/doi.org\/10.1017\/nlp.2024.20 (2025).","journal-title":"Natural Language Processing"},{"key":"33794_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101524","volume":"82","author":"SR Laskar","year":"2023","unstructured":"Laskar, S. R. et al. English-assamese neural machine translation using prior alignment and pre-trained language model. Computer Speech & Language 82, 101524. https:\/\/doi.org\/10.1016\/j.csl.2023.101524 (2023).","journal-title":"Computer Speech & Language"},{"key":"33794_CR14","doi-asserted-by":"publisher","unstructured":"Kim, Y. & Rush, A.\u00a0M. Sequence-level knowledge distillation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1317\u20131329, https:\/\/doi.org\/10.18653\/v1\/D16-1139 (Association for Computational Linguistics, Austin, Texas, 2016).","DOI":"10.18653\/v1\/D16-1139"},{"key":"33794_CR15","doi-asserted-by":"publisher","unstructured":"Dong, J. Transfer Learning-Based Neural Machine Translation for Low-Resource Languages. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) https:\/\/doi.org\/10.1145\/3618111 (2023). Just Accepted.","DOI":"10.1145\/3618111"},{"key":"33794_CR16","doi-asserted-by":"crossref","unstructured":"Roy, A., Ray, P., Maheshwari, A., Sarkar, S. & Goyal, P. Enhancing low-resource nmt with a multilingual encoder and knowledge distillation: A case study. In Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024), 64\u201373 (Association for Computational Linguistics, Bangkok, Thailand, 2024).","DOI":"10.18653\/v1\/2024.loresmt-1.7"},{"key":"33794_CR17","doi-asserted-by":"publisher","unstructured":"Yan, M., Wang, Y., Pang, K., Xie, M. & Li, J. Efficient Mixture of Experts Based on Large Language Models for Low-Resource Data Preprocessing. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD \u201924), 3690\u20133701, https:\/\/doi.org\/10.1145\/3637528.3671873 (Association for Computing Machinery, Barcelona, Spain, 2024).","DOI":"10.1145\/3637528.3671873"},{"key":"33794_CR18","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B. & Shazeer, N. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research 23, 1\u201339 (2022).","journal-title":"Journal of Machine Learning Research"},{"key":"33794_CR19","doi-asserted-by":"crossref","unstructured":"Elbayad, M., Sun, A.\u00a0Y. & Bhosale, S. Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.findings-acl.897"},{"key":"33794_CR20","unstructured":"Cruz Salinas, A.\u00a0F., Kumatani, K., Gmyr, R., Liu, L. & Shi, Y. Knowledge Distillation for Mixture of Experts Models in Speech Recognition. In Proceedings of the Conference on Speech Recognition and Processing (2022)."},{"key":"33794_CR21","unstructured":"Stenetorp, P., Yang, S., Yu, Y., Wang, M. & Ling, Z. Fast and lightweight neural machine translation with transformer-lite. arXiv preprint arXiv:2004.14888 (2020)."},{"key":"33794_CR22","unstructured":"Marianmt: A neural machine translation framework. https:\/\/marian-nmt.github.io\/. Accessed: 2025-07-11."},{"key":"33794_CR23","unstructured":"Enis, M., Hopkins, M. From llm to nmt: Advancing low-resource machine translation with claude. arXiv preprint arXiv:2403.07625 (2024)."},{"key":"33794_CR24","doi-asserted-by":"crossref","unstructured":"Ott, M. et al. fairseq: A fast, extensible toolkit for sequence modeling. In Proceedings of NAACL-HLT 2019: Demonstrations, 48\u201353 (2019).","DOI":"10.18653\/v1\/N19-4009"},{"key":"33794_CR25","unstructured":"Kingma, D.\u00a0P. & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"33794_CR26","doi-asserted-by":"crossref","unstructured":"Kudo, T., Richardson, J. Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 66\u201371 (2018).","DOI":"10.18653\/v1\/D18-2012"},{"key":"33794_CR27","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T. & Zhu, W.-J. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 311\u2013318 (ACL, 2002).","DOI":"10.3115\/1073083.1073135"},{"key":"33794_CR28","doi-asserted-by":"crossref","unstructured":"Post, M. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Machine Translation: Research Papers, 186\u2013191 (Association for Computational Linguistics, 2018).","DOI":"10.18653\/v1\/W18-6319"},{"key":"33794_CR29","doi-asserted-by":"crossref","unstructured":"Popovi?, M. chrf: character n-gram f-score for automatic mt evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, 392\u2013395 (2015).","DOI":"10.18653\/v1\/W15-3049"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33794-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33794-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33794-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T10:18:53Z","timestamp":1769595533000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-33794-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["33794"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-33794-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]},"assertion":[{"value":"13 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"All authors have read and agreed to the published version of the manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable. The study did not involve human participants.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}],"article-number":"3787"}}