{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:40:54Z","timestamp":1758044454173,"version":"3.44.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"10","funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"crossref","award":["202308050092"],"award-info":[{"award-number":["202308050092"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2025,10,31]]},"abstract":"<jats:p>Mixup, an interpolation-based method that implicitly generates synthetic examples for training, has shown effectiveness in tasks such as image and text classification. Standard mixup randomly interpolates two samples of images and their labels. In this article, we apply mixup to low-resource machine translation tasks by interpolating in the hidden space. We investigate the impact of different mixing coefficients on this technique. We also explore whether semantically related or unrelated samples provide more benefits for interpolation compared to random selection. To investigate this, we extend the standard mixup approach by selecting samples based on distance and experimenting with different sampling settings. Our experiments are conducted across several low-resource language pairs, including Lower Sorbian and Upper Sorbian, Lower Sorbian and German, and Upper Sorbian and German. Through systematic experiments on multiple language pairs, we evaluate the effectiveness of mixup data augmentation in improving low-resource machine translation performance. Our findings indicate that the standard mixup technique enhances the quality of machine translation, resulting in an average increase of 1.9 BLEU points over the baseline Transformer model. The choice of mixing coefficients has minimal impact on translation quality, which suggests that fine-tuning these coefficients is not essential to benefit from mixup. In addition, the standard mixup performs robustly, as selecting either the most similar or most dissimilar samples for mixing does not provide a significant improvement over it.<\/jats:p>","DOI":"10.1145\/3750043","type":"journal-article","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T11:55:59Z","timestamp":1753444559000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mixup Helps Translation, But Do the Coefficients and the Selection Strategy Influence Translation Quality?"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2489-158X","authenticated-orcid":false,"given":"Yifei","family":"Zhou","sequence":"first","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University","place":["Kitakyushu, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3059-4271","authenticated-orcid":false,"given":"Yves","family":"Lepage","sequence":"additional","affiliation":[{"name":"Graduate School of Information, Production and Systems, Waseda University","place":["Kitakyushu, Japan"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"e_1_3_3_2_2","first-page":"1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR 2018)","author":"Artetxe Mikel","year":"2018","unstructured":"Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018. Unsupervised neural machine translation. In Proceedings of the 6th International Conference on Learning Representations (ICLR 2018). International Conference on Learning Representations, Vancouver, BC, Canada, 1\u201312."},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.281"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.95"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.194"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/3368602"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.282"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.529"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1040"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1026"},{"key":"e_1_3_3_12_2","first-page":"765","volume-title":"Proceedings of the 5th Conference on Machine Translation","author":"Fraser Alexander","year":"2020","unstructured":"Alexander Fraser. 2020. Findings of the WMT 2020 shared tasks in unsupervised MT and very low resource supervised MT. In Proceedings of the 5th Conference on Machine Translation. Association for Computational Linguistics, Online, 765\u2013771."},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1555"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.447"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5822"},{"key":"e_1_3_3_16_2","unstructured":"Hongyu Guo Yongyi Mao and Richong Zhang. 2019. Augmenting data with mixup for sentence classification: An empirical study. arXiv:1905.08941. Retrieved from https:\/\/arxiv.org\/abs\/1905.08941"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013714"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00446"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/579"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"e_1_3_3_22_2","first-page":"1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR 2018)","author":"Lample Guillaume","year":"2018","unstructured":"Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc\u2019Aurelio Ranzato. 2018. Unsupervised machine translation using monolingual corpora only. In Proceedings of the 6th International Conference on Learning Representations (ICLR 2018). International Conference on Learning Representations, Vancouver, BC, Canada, 1\u201314."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.29"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.105"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3049011"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"e_1_3_3_27_2","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, 311\u2013318."},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3567592"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.67"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524300"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12007"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00139"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.305"},{"key":"e_1_3_3_37_2","first-page":"3104","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the Advances in Neural Information Processing Systems. Curran Associates, Inc., Montreal, Canada, 3104\u20133112."},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.533"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01858"},{"key":"e_1_3_3_41_2","series-title":"Proceedings of Machine Learning Research","first-page":"6438","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold mixup: Better representations by interpolating hidden states. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 97). PMLR, Long Beach, California, 6438\u20136447."},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1100"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.546"},{"key":"e_1_3_3_44_2","first-page":"801","volume-title":"Proceedings of the 7th Conference on Machine Translation (WMT)","author":"Marco Marion Weller-Di","year":"2022","unstructured":"Marion Weller-Di Marco and Alexander Fraser. 2022. Findings of the WMT 2022 shared tasks in unsupervised MT and very low resource supervised MT. In Proceedings of the 7th Conference on Machine Translation (WMT). Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (Hybrid), 801\u2013805."},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_3_46_2","first-page":"1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR 2018)","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Ciss\u00e9, Yann N. Dauphin, and David Lopez-Paz. 2018. mixup: Beyond empirical risk minimization. In Proceedings of the 6th International Conference on Learning Representations (ICLR 2018). International Conference on Learning Representations, Vancouver, BC, Canada, 1\u201313."},{"key":"e_1_3_3_47_2","first-page":"3788","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Zhang Shaokang","year":"2022","unstructured":"Shaokang Zhang, Lei Jiang, and Jianlong Tan. 2022. Dynamic nonlinear mixup with distance-based sample selection. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 3788\u20133797."},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1163"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3750043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T12:54:50Z","timestamp":1757681690000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3750043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":47,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,31]]}},"alternative-id":["10.1145\/3750043"],"URL":"https:\/\/doi.org\/10.1145\/3750043","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"type":"print","value":"2375-4699"},{"type":"electronic","value":"2375-4702"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"2025-01-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}