{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T08:04:12Z","timestamp":1784189052953,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234165","type":"print"},{"value":"9789819234172","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3417-2_3","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:10:50Z","timestamp":1784185850000},"page":"26-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MoSTE: A Spatio-Temporal Mixture of Experts Encoder for Low-Resource Multilingual Translation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6729-6036","authenticated-orcid":false,"given":"Kang","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2660-0163","authenticated-orcid":false,"given":"Xinyue","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6792-1355","authenticated-orcid":false,"given":"Fang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4435-2745","authenticated-orcid":false,"given":"Zhenyuan","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3225-939X","authenticated-orcid":false,"given":"Binqing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5758-4613","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1162\/tacl_a_00065","volume":"5","author":"M Johnson","year":"2017","unstructured":"Johnson, M., Schuster, M., Le, Q., et al.: Google\u2019s multilingual neural machine translation system: enabling zero-shot translation. Trans. Assoc. Comput. Linguist. 5, 339\u2013351 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"3_CR2","unstructured":"Costa-Juss\u00e0, M.R., Cross, J., \u00c7elebi, O., et al.: No language left behind: Scaling human-centered machine translation. arXiv preprint https:\/\/arxiv.org\/abs\/2207.04672. (2022)"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"4074","DOI":"10.18653\/v1\/2024.emnlp-main.236","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"TA Chang","year":"2024","unstructured":"Chang, T.A., Arnett, C., Tu, Z., et al.: When is multilinguality a curse? language modeling for 250 high-and low-resource languages. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 4074\u20134096 (2024)"},{"key":"3_CR4","doi-asserted-by":"publisher","first-page":"5486","DOI":"10.18653\/v1\/2022.acl-long.376","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"D Blasi","year":"2022","unstructured":"Blasi, D., Anastasopoulos, A., Neubig, G.: Systematic inequalities in language technology performance across the world\u2019s languages. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5486\u20135505 (2022)"},{"key":"3_CR5","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint https:\/\/arxiv.org\/abs\/1701.06538. (2017)"},{"issue":"120","key":"3_CR6","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. J. Mach. Learn. Res. 23(120), 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"4978","DOI":"10.18653\/v1\/2023.emnlp-main.303","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"S Li","year":"2023","unstructured":"Li, S., Wei, X., Zhu, S., et al.: MMNMT: modularizing multilingual neural machine translation with flexibly assembled MoE and dense blocks. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 4978\u20134990 (2023)"},{"key":"3_CR8","first-page":"1011","volume-title":"Proceedings of the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","author":"L Huang","year":"2025","unstructured":"Huang, L., Bu, M., Feng, Y.: Moce: adaptive mixture of contextualization experts for byte-based neural machine translation. In: Proceedings of the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 1011\u20131028 (2025)"},{"key":"3_CR9","unstructured":"Wu, F., Fan, A., Baevski, A., et al.: Pay less attention with lightweight and dynamic convolutions. arXiv preprint arXiv:1901.10430. (2019)"},{"key":"3_CR10","doi-asserted-by":"publisher","first-page":"4449","DOI":"10.18653\/v1\/D18-1475","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"B Yang","year":"2018","unstructured":"Yang, B., Tu, Z., Wong, D.F., et al.: Modeling localness for self-attention networks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4449\u20134458 (2018)"},{"issue":"6","key":"3_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3530811","volume":"55","author":"Y Tay","year":"2022","unstructured":"Tay, Y., Dehghani, M., Bahri, D., et al.: Efficient transformers: a survey. ACM Comput. Surv. 55(6), 1\u201328 (2022)","journal-title":"ACM Comput. Surv."},{"key":"3_CR12","first-page":"11769","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"MM Rahman","year":"2024","unstructured":"Rahman, M.M., Munir, M., Marculescu, R.: Emcad: Efficient multi-scale convolutional attention decoding for medical image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11769\u201311779 (2024)"},{"issue":"12","key":"3_CR13","first-page":"14329","volume":"37","author":"Y Liang","year":"2023","unstructured":"Liang, Y., Xia, Y., Ke, S., et al.: Airformer: predicting nationwide air quality in China with transformers. Proc. AAAI Conf. Artif. Intell. 37(12), 14329\u201314337 (2023)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"3_CR14","first-page":"529","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)","author":"Y Qi","year":"2018","unstructured":"Qi, Y., Sachan, D., Felix, M., et al.: When and why are pre-trained word embeddings useful for neural machine translation? In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pp. 529\u2013535 (2018)"},{"key":"3_CR15","doi-asserted-by":"publisher","first-page":"8526","DOI":"10.18653\/v1\/2020.acl-main.754","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"X Wang","year":"2020","unstructured":"Wang, X., Tsvetkov, Y., Neubig, G.: Balancing training for multilingual neural machine translation. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8526\u20138537 (2020)"},{"issue":"107","key":"3_CR16","first-page":"1","volume":"22","author":"A Fan","year":"2021","unstructured":"Fan, A., Bhosale, S., Schwenk, H., et al.: Beyond english-centric multilingual machine translation. J. Mach. Learn. Res. 22(107), 1\u201348 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR17","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.18653\/v1\/D19-1165","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"A Bapna","year":"2019","unstructured":"Bapna, A., Firat, O.: Simple, scalable adaptation for neural machine translation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1538\u20131548 (2019)"},{"key":"3_CR18","unstructured":"Lepikhin, D, Lee, HJ, Xu, Y, et al.: Gshard: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668, (2020)"},{"key":"3_CR19","volume-title":"International Conference on Learning Representations","author":"B Zhang","year":"2021","unstructured":"Zhang, B., Bapna, A., Sennrich, R., et al.: Share or not? learning to schedule language-specific capacity for multilingual translation. In: International Conference on Learning Representations (2021)"},{"key":"3_CR20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Proces. Syst. 30 (2017)"},{"key":"3_CR21","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150. (2020)"},{"key":"3_CR22","unstructured":"Child, R., Gray, S., Radford, A., et al.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509. (2019)"},{"key":"3_CR23","first-page":"2793","volume-title":"International Conference on Machine Learning. PMLR","author":"Y Dong","year":"2021","unstructured":"Dong, Y., Cordonnier, J.B., Loukas, A.: Attention is not all you need: pure attention loses rank doubly exponentially with depth. In: International Conference on Machine Learning. PMLR, pp. 2793\u20132803 (2021)"},{"key":"3_CR24","doi-asserted-by":"publisher","first-page":"211","DOI":"10.18653\/v1\/P19-1021","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"R Sennrich","year":"2019","unstructured":"Sennrich, R., Zhang, B.: Revisiting low-resource neural machine translation: a case study. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 211\u2013221 (2019)"},{"key":"3_CR25","unstructured":"Shaham, U., Levy, O.: NMT without embeddings: towards subword-free representations. arXiv preprint arXiv:2104.08961. (2021)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Huang, L., Feng, Y.: Integrating multi-scale contextualized information for byte-based neural machine translation (MSC). Proc. EMNLP. (2024)","DOI":"10.18653\/v1\/2024.findings-acl.583"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Post, M.: A call for clarity in reporting BLEU scores. arXiv preprint arXiv:1804.08771. (2018)","DOI":"10.18653\/v1\/W18-6319"},{"key":"3_CR28","first-page":"291","volume":"10","author":"L Xue","year":"2022","unstructured":"Xue, L., Barua, A., Constant, N., et al.: ByT5: towards a token-free future with pre-trained byte-to-byte models. Trans. ACL. 10, 291\u2013310 (2022)","journal-title":"Trans. ACL"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3417-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:10:54Z","timestamp":1784185854000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3417-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234165","9789819234172"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3417-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}