{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:52:44Z","timestamp":1781931164072,"version":"3.54.5"},"reference-count":62,"publisher":"Association for Natural Language Processing","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Natural Language Processing"],"published-print":{"date-parts":[[2026]]},"DOI":"10.5715\/jnlp.33.809","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:11:45Z","timestamp":1781475105000},"page":"809-847","source":"Crossref","is-referenced-by-count":0,"title":["MITRE: Efficient Pre-trained Models for Multilingual Neural Machine Translation with Registering"],"prefix":"10.5715","volume":"33","author":[{"given":"Zhi","family":"Qu","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Wang","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiannan","family":"Mao","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Tei","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideki","family":"Tanaka","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masao","family":"Utiyama","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taro","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3685","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"Aharoni, R., Johnson, M., and Firat, O. (2019). \u201cMassively Multilingual Neural Machine Translation.\u201d <i>CoRR<\/i>, <b>abs\/1903.00089<\/b>.","DOI":"10.18653\/v1\/N19-1388"},{"key":"2","unstructured":"Alves, D. M., Pombal, J., Guerreiro, N. M., Martins, P. H., Alves, J., Farajian, A., Peters, B., Rei, R., Fernandes, P., Agrawal, S., Colombo, P., de Souza, J. G. C., and Martins, A. (2024). \u201cTower: An Open Multilingual Large Language Model for Translation-Related Tasks.\u201d In <i>1st Conference on Language Modeling<\/i>."},{"key":"3","unstructured":"Arivazhagan, N., Bapna, A., Firat, O., Aharoni, R., Johnson, M., and Macherey, W. (2019a). \u201cThe Missing Ingredient in Zero-Shot Neural Machine Translation.\u201d <i>CoRR<\/i>, <b>abs\/1903.07091<\/b>."},{"key":"4","unstructured":"Arivazhagan, N., Bapna, A., Firat, O., Lepikhin, D., Johnson, M., Krikun, M., Chen, M. X., Cao, Y., Foster, G., Cherry, C., Macherey, W., Chen, Z., and Wu, Y. (2019b). \u201cMassively Multilingual Neural Machine Translation in the Wild: Findings and Challenges.\u201d <i>CoRR<\/i>, <b>abs\/1907.05019<\/b>."},{"key":"5","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. (2020). \u201cLanguage Models are Few-Shot Learners.\u201d In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H. (Eds.), <i>Advances in Neural Information Processing Systems<\/i>, Vol. 33, pp. 1877\u20131901. Curran Associates, Inc."},{"key":"6","doi-asserted-by":"crossref","unstructured":"Bu, M., Gu, S., and Feng, Y. (2024). \u201cImproving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features.\u201d In Ku, L.-W., Martins, A., and Srikumar, V. (Eds.), <i>Findings of the Association for Computational Linguistics ACL 2024<\/i>, pp. 10410\u201310423, Bangkok, Thailand and Virtual Meeting. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-acl.620"},{"key":"7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Qu, Z., Kamigaito, H., and Watanabe, T. (2024). \u201cExploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation.\u201d In Al-Onaizan, Y., Bansal, M., and Chen, Y.-N. (Eds.), <i>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 21142\u201321157, Miami, Florida, USA. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.emnlp-main.1177"},{"key":"8","doi-asserted-by":"crossref","unstructured":"Chen, L., Ma, S., Zhang, D., Wei, F., and Chang, B. (2023). \u201cOn the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation.\u201d In <i>Findings of the Association for Computational Linguistics: ACL 2023<\/i>, pp. 9542\u20139558, Toronto, Canada. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-acl.608"},{"key":"9","unstructured":"Dong, L., Yang, N., Wang, W., Wei, F., Liu, X., Wang, Y., Gao, J., Zhou, M., and Hon, H.-W. (2019). \u201cUnified Language Model Pre-training for Natural Language Understanding and Generation.\u201d In Wallach, H., Larochelle, H., Beygelzimer, A., d&apos;Alch\u00e9-Buc, F., Fox, E., and Garnett, R. (Eds.), <i>Advances in Neural Information Processing Systems<\/i>, Vol. 32. Curran Associates, Inc."},{"key":"10","doi-asserted-by":"crossref","unstructured":"Edunov, S., Ott, M., Auli, M., and Grangier, D. (2018). \u201cUnderstanding Back-Translation at Scale.\u201d In Riloff, E., Chiang, D., Hockenmaier, J., and Tsujii, J. (Eds.), <i>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 489\u2013500, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-1045"},{"key":"11","doi-asserted-by":"crossref","unstructured":"Eriguchi, A., Xie, S., Qin, T., and Hassan, H. (2022). \u201cBuilding Multilingual Machine Translation Systems That Serve Arbitrary XY Translations.\u201d In Carpuat, M., de Marneffe, M.-C., and Meza Ruiz, I. V. (Eds.), <i>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies<\/i>, pp. 600\u2013606, Seattle, United States. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.naacl-main.44"},{"key":"12","unstructured":"Fan, A., Bhosale, S., Schwenk, H., Ma, Z., El-Kishky, A., Goyal, S., Baines, M., Celebi, O., Wenzek, G., Chaudhary, V., Goyal, N., Birch, T., Liptchinsky, V., Edunov, S., Grave, E., Auli, M., and Joulin, A. (2021). \u201cBeyond English-centric Multilingual Machine Translation.\u201d <i>The Journal of Machine Learning Research<\/i>, <b>22<\/b> (1)."},{"key":"13","doi-asserted-by":"crossref","unstructured":"Galiano-Jim\u00e9nez, A., P\u00e9rez-Ortiz, J. A., S\u00e1nchez-Mart\u00ednez, F., and S\u00e1nchez-Cartagena, V. M. (2025). \u201cBeyond the Mode: Sequence-Level Distillation of Multilingual Translation Models for Low-Resource Language Pairs.\u201d In Chiruzzo, L., Ritter, A., and Wang, L. (Eds.), <i>Findings of the Association for Computational Linguistics: NAACL 2025<\/i>, pp. 6661\u20136676, Albuquerque, New Mexico. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.findings-naacl.372"},{"key":"14","doi-asserted-by":"crossref","unstructured":"Gao, Y., Herold, C., Yang, Z., and Ney, H. (2022). \u201cIs Encoder-Decoder Redundant for Neural Machine Translation?\u201d In He, Y., Ji, H., Li, S., Liu, Y., and Chang, C.-H. (Eds.), <i>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)<\/i>, pp. 562\u2013574, Online only. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.aacl-main.43"},{"key":"15","doi-asserted-by":"crossref","unstructured":"Goyal, N., Gao, C., Chaudhary, V., Chen, P.-J., Wenzek, G., Ju, D., Krishnan, S., Ranzato, M., Guzman, F., and Fan, A. (2021). \u201cThe FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation.\u201d <i>CoRR<\/i>, <b>abs\/2106.03193<\/b>.","DOI":"10.1162\/tacl_a_00474"},{"key":"16","doi-asserted-by":"crossref","unstructured":"Gu, J., Wang, Y., Cho, K., and Li, V. O. (2019). \u201cImproved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations.\u201d In <i>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 1258\u20131268, Florence, Italy. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1121"},{"key":"17","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). \u201cDistilling the Knowledge in a Neural Network.\u201d <i>CoRR<\/i>, <b>abs\/1503.02531<\/b>."},{"key":"18","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022). \u201cLoRA: Low-Rank Adaptation of Large Language Models.\u201d In <i>International Conference on Learning Representations<\/i>."},{"key":"19","doi-asserted-by":"crossref","unstructured":"Hudi, F., Qu, Z., Kamigaito, H., and Watanabe, T. (2024). \u201cDisentangling Pretrained Representation to Leverage Low-Resource Languages in Multilingual Machine Translation.\u201d In Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., and Xue, N. (Eds.), <i>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)<\/i>, pp. 4978\u20134989, Torino, Italia. ELRA and ICCL.","DOI":"10.63317\/4kp88e3pkpxs"},{"key":"20","doi-asserted-by":"crossref","unstructured":"Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Vi\u00e9gas, F., Wattenberg, M., Corrado, G., Hughes, M., and Dean, J. (2017). \u201cGoogle\u2019s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation.\u201d <i>Transactions of the Association for Computational Linguistics<\/i>, <b>5<\/b>, pp. 339\u2013351.","DOI":"10.1162\/tacl_a_00065"},{"key":"21","unstructured":"Kingma, D. P., and Ba, J. (2017). \u201cAdam: A Method for Stochastic Optimization.\u201d <i>CoRR<\/i>, <b>abs\/1412.6980<\/b>."},{"key":"22","unstructured":"Koehn, P. (2004). \u201cStatistical Significance Tests for Machine Translation Evaluation.\u201d In Lin, D., and Wu, D. (Eds.), <i>Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 388\u2013395, Barcelona, Spain. Association for Computational Linguistics."},{"key":"23","doi-asserted-by":"crossref","unstructured":"Kudo, T. (2018). \u201cSubword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates.\u201d In Gurevych, I., and Miyao, Y. (Eds.), <i>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 66\u201375, Melbourne, Australia. Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1007"},{"key":"24","doi-asserted-by":"crossref","unstructured":"Kudo, T., and Richardson, J. (2018). \u201cSentencePiece: A Simple and Language Independent Subword Tokenizer and Detokenizer for Neural Text Processing.\u201d In <i>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations<\/i>, pp. 66\u201371, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/D18-2012"},{"key":"25","doi-asserted-by":"crossref","unstructured":"Liu, D., Niehues, J., Cross, J., Guzm\u00e1n, F., and Li, X. (2021). \u201cImproving Zero-Shot Translation by Disentangling Positional Information.\u201d In <i>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)<\/i>, pp. 1259\u20131273, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.acl-long.101"},{"key":"26","unstructured":"Moslem, Y., Haque, R., Kelleher, J. D., and Way, A. (2023). \u201cAdaptive Machine Translation with Large Language Models.\u201d In Nurminen, M., Brenner, J., Koponen, M., Latomaa, S., Mikhailov, M., Schierl, F., Ranasinghe, T., Vanmassenhove, E., Vidal, S. A., Aranberri, N., Nunziatini, M., Escart\u00edn, C. P., Forcada, M., Popovic, M., Scarton, C., and Moniz, H. (Eds.), <i>Proceedings of the 24th Annual Conference of the European Association for Machine Translation<\/i>, pp. 227\u2013237, Tampere, Finland. European Association for Machine Translation."},{"key":"27","doi-asserted-by":"crossref","unstructured":"Mullov, C., Pham, Q., and Waibel, A. (2024). \u201cDecoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages.\u201d In Ku, L.-W., Martins, A., and Srikumar, V. (Eds.), <i>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 6693\u20136709, Bangkok, Thailand. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.acl-long.362"},{"key":"28","unstructured":"NLLB Team (2022). \u201cNo Language Left Behind: Scaling Human-Centered Machine Translation.\u201d <i>CoRR<\/i>, <b>abs\/2207.04672<\/b>."},{"key":"29","unstructured":"OpenAI (2024). \u201cGPT-4 Technical Report.\u201d <i>CoRR<\/i>, <b>abs\/2303.08774<\/b>."},{"key":"30","doi-asserted-by":"crossref","unstructured":"Ott, M., Edunov, S., Baevski, A., Fan, A., Gross, S., Ng, N., Grangier, D., and Auli, M. (2019). \u201cfairseq: A Fast, Extensible Toolkit for Sequence Modeling.\u201d In <i>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)<\/i>, pp. 48\u201353, Minneapolis, Minnesota. Association for Computational Linguistics.","DOI":"10.18653\/v1\/N19-4009"},{"key":"31","doi-asserted-by":"crossref","unstructured":"Pan, X., Wang, M., Wu, L., and Li, L. (2021). \u201cContrastive Learning for Many-to-many Multilingual Neural Machine Translation.\u201d In <i>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)<\/i>, pp. 244\u2013258, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.acl-long.21"},{"key":"32","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., and Zhu, W.-J. (2002). \u201cBleu: a Method for Automatic Evaluation of Machine Translation.\u201d In <i>Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 311\u2013318, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.","DOI":"10.3115\/1073083.1073135"},{"key":"33","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, M. (2015). \u201cchrF: Character n-gram F-score for Automatic MT Evaluation.\u201d In Bojar, O., Chatterjee, R., Federmann, C., Haddow, B., Hokamp, C., Huck, M., Logacheva, V., and Pecina, P. (Eds.), <i>Proceedings of the 10th Workshop on Statistical Machine Translation<\/i>, pp. 392\u2013395, Lisbon, Portugal. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W15-3049"},{"key":"34","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, M. (2017). \u201cchrF++: Words Helping Character n-grams.\u201d In Bojar, O., Buck, C., Chatterjee, R., Federmann, C., Graham, Y., Haddow, B., Huck, M., Yepes, A. J., Koehn, P., and Kreutzer, J. (Eds.), <i>Proceedings of the 2nd Conference on Machine Translation<\/i>, pp. 612\u2013618, Copenhagen, Denmark. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W17-4770"},{"key":"35","doi-asserted-by":"crossref","unstructured":"Post, M. (2018). \u201cA Call for Clarity in Reporting BLEU Scores.\u201d In <i>Proceedings of the 3rd Conference on Machine Translation: Research Papers<\/i>, pp. 186\u2013191, Brussels, Belgium. Association for Computational Linguistics.","DOI":"10.18653\/v1\/W18-6319"},{"key":"36","doi-asserted-by":"crossref","unstructured":"Proietti, L., Perrella, S., and Navigli, R. (2025). \u201cHas Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress.\u201d In Che, W., Nabende, J., Shutova, E., and Pilehvar, M. T. (Eds.), <i>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)<\/i>, pp. 790\u2013813, Vienna, Austria. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.acl-short.63"},{"key":"37","unstructured":"Qu, Z., Ding, C., and Watanabe, T. (2025). \u201cLanguages Transferred Within the Encoder: On Representation Transfer in Zero-Shot Multilingual Translation.\u201d In Bouillon, P., Gerlach, J., Girletti, S., Volkart, L., Rubino, R., Sennrich, R., Farinha, A. C., Gaido, M., Daems, J., Kenny, D., Moniz, H., and Szoc, S. (Eds.), <i>Proceedings of Machine Translation Summit XX: Volume 1<\/i>, pp. 81\u201398, Geneva, Switzerland. European Association for Machine Translation."},{"key":"38","unstructured":"Qu, Z., Wang, Y., Ding, C., Tanaka, H., Utiyama, M., and Watanabe, T. (2024). \u201cImproving Language Transfer Capability of Decoder-only Architecture in Multilingual Neural Machine Translation.\u201d <i>CoRR<\/i>, <b>abs\/2412.02101<\/b>."},{"key":"39","doi-asserted-by":"crossref","unstructured":"Qu, Z., Wang, Y., Mao, J., Ding, C., Tanaka, H., Utiyama, M., and Watanabe, T. (2025). \u201cRegistering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation.\u201d In Che, W., Nabende, J., Shutova, E., and Pilehvar, M. T. (Eds.), <i>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<\/i>, pp. 21687\u201321706, Vienna, Austria. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.acl-long.1052"},{"key":"40","unstructured":"Qu, Z., and Watanabe, T. (2022). \u201cAdapting to Non-Centered Languages for Zero-shot Multilingual Translation.\u201d In <i>Proceedings of the 29th International Conference on Computational Linguistics<\/i>, pp. 5251\u20135265, Gyeongju, Republic of Korea. International Committee on Computational Linguistics."},{"key":"41","unstructured":"Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2018). \u201cImproving Language Understanding by Generative Pre-training.\u201d <i>OpenAI<\/i>."},{"key":"42","doi-asserted-by":"crossref","unstructured":"Rei, R., C. de Souza, J. G., Alves, D., Zerva, C., Farinha, A. C., Glushkova, T., Lavie, A., Coheur, L., and Martins, A. F. T. (2022). \u201cCOMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task.\u201d In Koehn, P., Barrault, L., Bojar, O., Bougares, F., Chatterjee, R., Costa-juss\u00e0, M. R., Federmann, C., Fishel, M., Fraser, A., Freitag, M., Graham, Y., Grundkiewicz, R., Guzman, P., Haddow, B., Huck, M., Jimeno Yepes, A., Kocmi, T., Martins, A., Morishita, M., Monz, C., Nagata, M., Nakazawa, T., Negri, M., N\u00e9v\u00e9ol, A., Neves, M., Popel, M., Turchi, M., and Zampieri, M. (Eds.), <i>Proceedings of the 7th Conference on Machine Translation (WMT)<\/i>, pp. 578\u2013585, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.","DOI":"10.18653\/v1\/2022.wmt-1.52"},{"key":"43","doi-asserted-by":"crossref","unstructured":"Rei, R., Stewart, C., Farinha, A. C., and Lavie, A. (2020). \u201cCOMET: A Neural Framework for MT Evaluation.\u201d In Webber, B., Cohn, T., He, Y., and Liu, Y. (Eds.), <i>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)<\/i>, pp. 2685\u20132702, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"44","doi-asserted-by":"crossref","unstructured":"Rios, A., M\u00fcller, M., and Sennrich, R. (2020). \u201cSubword Segmentation and a Single Bridge Language Affect Zero-Shot Neural Machine Translation.\u201d In Barrault, L., Bojar, O., Bougares, F., Chatterjee, R., Costa-juss\u00e0, M. R., Federmann, C., Fishel, M., Fraser, A., Graham, Y., Guzman, P., Haddow, B., Huck, M., Yepes, A. J., Koehn, P., Martins, A., Morishita, M., Monz, C., Nagata, M., Nakazawa, T., and Negri, M. (Eds.), <i>Proceedings of the 5th Conference on Machine Translation<\/i>, pp. 528\u2013537, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.wmt-1.64"},{"key":"45","doi-asserted-by":"crossref","unstructured":"Stap, D., Niculae, V., and Monz, C. (2023). \u201cViewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens.\u201d In Bouamor, H., Pino, J., and Bali, K. (Eds.), <i>Findings of the Association for Computational Linguistics: EMNLP 2023<\/i>, pp. 14973\u201314987, Singapore. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.findings-emnlp.998"},{"key":"46","doi-asserted-by":"crossref","unstructured":"Sun, Z., Liu, Y., Meng, F., Xu, J., Chen, Y., and Zhou, J. (2024). \u201cLCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation.\u201d In Ku, L.-W., Martins, A., and Srikumar, V. (Eds.), <i>Findings of the Association for Computational Linguistics ACL 2024<\/i>, pp. 9201\u20139214, Bangkok, Thailand and Virtual Meeting. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-acl.547"},{"key":"47","unstructured":"Sutskever, I., Vinyals, O., and Le, Q. V. (2014). \u201cSequence to Sequence Learning with Neural Networks.\u201d In <i>Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2<\/i>, NIPS\u201914, pp. 3104\u20133112, Cambridge, MA, USA. MIT Press."},{"key":"48","doi-asserted-by":"crossref","unstructured":"Tan, S., and Monz, C. (2023). \u201cTowards a Better Understanding of Variations in Zero-Shot Neural Machine Translation Performance.\u201d In Bouamor, H., Pino, J., and Bali, K. (Eds.), <i>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing<\/i>, pp. 13553\u201313568, Singapore. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2023.emnlp-main.836"},{"key":"49","unstructured":"van der Maaten, L., and Hinton, G. (2008). \u201cVisualizing Data using t-SNE.\u201d <i>Journal of Machine Learning Research<\/i>, <b>9<\/b> (86), pp. 2579\u20132605."},{"key":"50","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., and Polosukhin, I. (2017). \u201cAttention Is All You Need.\u201d In Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (Eds.), <i>Advances in Neural Information Processing Systems<\/i>, Vol. 30. Curran Associates, Inc."},{"key":"51","unstructured":"Wang, T., Roberts, A., Hesslow, D., Scao, T. L., Chung, H. W., Beltagy, I., Launay, J., and Raffel, C. (2022). \u201cWhat Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?\u201d <i>CoRR<\/i>, <b>abs\/2204.05832<\/b>."},{"key":"52","unstructured":"Wang, Y., Zhong, W., Li, L., Mi, F., Zeng, X., Huang, W., Shang, L., Jiang, X., and Liu, Q. (2023). \u201cAligning Large Language Models with Human: A Survey.\u201d <i>CoRR<\/i>, <b>abs\/2307.12966<\/b>."},{"key":"53","doi-asserted-by":"crossref","unstructured":"Wu, D., Tan, S., Meng, Y., Stap, D., and Monz, C. (2024). \u201cHow Far Can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data.\u201d In Ku, L.-W., Martins, A., and Srikumar, V. (Eds.), <i>Findings of the Association for Computational Linguistics: ACL 2024<\/i>, pp. 15092\u201315108, Bangkok, Thailand. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-acl.896"},{"key":"54","doi-asserted-by":"crossref","unstructured":"Wu, L., Cheng, S., Wang, M., and Li, L. (2021). \u201cLanguage Tags Matter for Zero-Shot Neural Machine Translation.\u201d In Zong, C., Xia, F., Li, W., and Navigli, R. (Eds.), <i>Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021<\/i>, pp. 3001\u20133007, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2021.findings-acl.264"},{"key":"55","unstructured":"Xu, H., Kim, Y. J., Sharaf, A., and Awadalla, H. H. (2024). \u201cA Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models.\u201d In <i>The 12th International Conference on Learning Representations<\/i>."},{"key":"56","unstructured":"Xu, H., Murray, K., Koehn, P., Hoang, H., Eriguchi, A., and Khayrallah, H. (2025). \u201cX-ALMA: Plug &amp; Play Modules and Adaptive Rejection for Quality Translation at Scale.\u201d In <i>The 13th International Conference on Learning Representations<\/i>."},{"key":"57","unstructured":"Yang, W., Li, C., Zhang, J., and Zong, C. (2023). \u201cBigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages.\u201d <i>CoRR<\/i>, <b>abs\/2305.18098<\/b>."},{"key":"58","unstructured":"Zhang, B., Bapna, A., Sennrich, R., and Firat, O. (2021). \u201cShare or Not? Learning to Schedule Language-Specific Capacity for Multilingual Translation.\u201d In <i>International Conference on Learning Representations<\/i>."},{"key":"59","unstructured":"Zhang, B., Ghorbani, B., Bapna, A., Cheng, Y., Garcia, X., Shen, J., and Firat, O. (2022). \u201cExamining Scaling and Transfer of Language Model Architectures for Machine Translation.\u201d In Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., and Sabato, S. (Eds.), <i>Proceedings of the 39th International Conference on Machine Learning<\/i>, Vol. 162 of <i>Proceedings of Machine Learning Research<\/i>, pp. 26176\u201326192. PMLR."},{"key":"60","doi-asserted-by":"crossref","unstructured":"Zhang, B., Williams, P., Titov, I., and Sennrich, R. (2020). \u201cImproving Massively Multilingual Neural Machine Translation and Zero-Shot Translation.\u201d In <i>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics<\/i>, pp. 1628\u20131639, Online. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2020.acl-main.148"},{"key":"61","doi-asserted-by":"crossref","unstructured":"Zhu, W., Liu, H., Dong, Q., Xu, J., Huang, S., Kong, L., Chen, J., and Li, L. (2024). \u201cMultilingual Machine Translation with Large Language Models: Empirical Results and Analysis.\u201d In Duh, K., Gomez, H., and Bethard, S. (Eds.), <i>Findings of the Association for Computational Linguistics: NAACL 2024<\/i>, pp. 2765\u20132781, Mexico City, Mexico. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2024.findings-naacl.176"},{"key":"62","doi-asserted-by":"crossref","unstructured":"Zou, W., Yang, S., Bao, Y., Huang, S., Chen, J., and Cheng, S. (2025). \u201cTRANS-ZERO: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Data.\u201d In Che, W., Nabende, J., Shutova, E., and Pilehvar, M. T. (Eds.), <i>Findings of the Association for Computational Linguistics: ACL 2025<\/i>, pp. 12337\u201312347, Vienna, Austria. Association for Computational Linguistics.","DOI":"10.18653\/v1\/2025.findings-acl.637"}],"container-title":["Journal of Natural Language Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/33\/2\/33_809\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:44:41Z","timestamp":1781930681000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/33\/2\/33_809\/_article\/-char\/ja\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":62,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.5715\/jnlp.33.809","relation":{},"ISSN":["1340-7619","2185-8314"],"issn-type":[{"value":"1340-7619","type":"print"},{"value":"2185-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}