{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:46:09Z","timestamp":1777639569503,"version":"3.51.4"},"reference-count":36,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2024,1,1]]},"DOI":"10.1587\/transinf.2023edp7048","type":"journal-article","created":{"date-parts":[[2023,12,31]],"date-time":"2023-12-31T22:39:14Z","timestamp":1704062354000},"page":"135-143","source":"Crossref","is-referenced-by-count":2,"title":["Inference Discrepancy Based Curriculum Learning for Neural Machine Translation"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Lei","family":"ZHOU","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryohei","family":"SASANO","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"TAKEDA","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J.L. Elman, \u201cLearning and development in neural networks: The importance of starting small,\u201d Cognition, vol.48, no.1, pp.71-99, 1993. 10.1016\/0010-0277(93)90058-4","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] T. Kocmi and O. Bojar, \u201cCurriculum learning and minibatch bucketing in neural machine translation,\u201d RANLP, Varna, Bulgaria, pp.379-386, INCOMA Ltd., 2017. 10.26615\/978-954-452-049-6_050","DOI":"10.26615\/978-954-452-049-6_050"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] E.A. Platanios, O. Stretcu, G. Neubig, B. Poczos, and T. Mitchell, \u201cCompetence-based curriculum learning for neural machine translation,\u201d NAACL, Minneapolis, Minnesota, pp.1162-1172, Association for Computational Linguistics, 2019. 10.18653\/v1\/n19-1119","DOI":"10.18653\/v1\/N19-1119"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] X. Liu, H. Lai, D.F. Wong, and L.S. Chao, \u201cNorm-based curriculum learning for neural machine translation,\u201d ACL, Online, pp.427-436, Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.acl-main.41","DOI":"10.18653\/v1\/2020.acl-main.41"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] Z.-Y. Dou, A. Anastasopoulos, and G. Neubig, \u201cDynamic data selection and weighting for iterative back-translation,\u201d EMNLP, Online, pp.5894-5904, Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.emnlp-main.475","DOI":"10.18653\/v1\/2020.emnlp-main.475"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] T. Mohiuddin, P. Koehn, V. Chaudhary, J. Cross, S. Bhosale, and S. Joty, \u201cData selection curriculum for neural machine translation,\u201d ArXiv, vol.abs\/2203.13867, 2022.","DOI":"10.18653\/v1\/2022.findings-emnlp.113"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] Y. Zhou, B. Yang, D.F. Wong, Y. Wan, and L.S. Chao, \u201cUncertainty-aware curriculum learning for neural machine translation,\u201d ACL, Online, pp.6934-6944, Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.acl-main.620","DOI":"10.18653\/v1\/2020.acl-main.620"},{"key":"8","unstructured":"[8] X. Zhang, G. Kumar, H. Khayrallah, K. Murray, J. Gwinnup, M.J. Martindale, P. McNamee, K. Duh, and M. Carpuat, \u201cAn empirical exploration of curriculum learning for neural machine translation,\u201d ArXiv, vol.abs\/1811.00739, 2018."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] C. Xu, B. Hu, Y. Jiang, K. Feng, Z. Wang, S. Huang, Q. Ju, T. Xiao, and J. Zhu, \u201cDynamic curriculum learning for low-resource neural machine translation,\u201d COLING, Barcelona, Spain (Online), pp.3977-3989, International Committee on Computational Linguistics, 2020. 10.18653\/v1\/2020.coling-main.352","DOI":"10.18653\/v1\/2020.coling-main.352"},{"key":"10","unstructured":"[10] M. Ranzato, S. Chopra, M. Auli, and W. Zaremba, \u201cSequence level training with recurrent neural networks,\u201d ICLR (Poster), 2016."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] W. Zhang, Y. Feng, F. Meng, D. You, and Q. Liu, \u201cBridging the gap between training and inference for neural machine translation,\u201d ACL, Florence, Italy, pp.4334-4343, Association for Computational Linguistics, July 2019. 10.18653\/v1\/p19-1426","DOI":"10.18653\/v1\/P19-1426"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] Y. Bengio, J. Louradour, R. Collobert, and J. Weston, \u201cCurriculum learning,\u201d Proc. 26th Annual International Conference on Machine Learning, New York, NY, USA, pp.41-48, Association for Computing Machinery, 2009. 10.1145\/1553374.1553380","DOI":"10.1145\/1553374.1553380"},{"key":"13","unstructured":"[13] V. Cirik, E. Hovy, and L.P. Morency, \u201cVisualizing and understanding curriculum learning for long short-term memory networks,\u201d ArXiv, vol.abs\/1611.06204, 2016."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] X. Zhang, P. Shapiro, G. Kumar, P. McNamee, M. Carpuat, and K. Duh, \u201cCurriculum learning for domain adaptation in neural machine translation,\u201d NAACL, Minneapolis, Minnesota, pp.1903-1915, Association for Computational Linguistics, 2019. 10.18653\/v1\/n19-1189","DOI":"10.18653\/v1\/N19-1189"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] L. Zhou, L. Ding, K. Duh, S. Watanabe, R. Sasano, and K. Takeda, \u201cSelf-guided curriculum learning for neural machine translation,\u201d IWSLT, Bangkok, Thailand (online), Association for Computational Linguistics, Aug. 2021. 10.18653\/v1\/2021.iwslt-1.25","DOI":"10.18653\/v1\/2021.iwslt-1.25"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] M. Zhang, F. Meng, Y. Tong, and J. Zhou, \u201cCompetence-based curriculum learning for multilingual machine translation,\u201d EMNLP, 2021. 10.18653\/v1\/2021.findings-emnlp.212","DOI":"10.18653\/v1\/2021.findings-emnlp.212"},{"key":"17","unstructured":"[17] M.P. Kumar, B. Packer, and D. Koller, \u201cSelf-paced learning for latent variable models,\u201d NIPS, p.1189-1197, Curran Associates Inc., 2010."},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] L. Jiang, D. Meng, Q. Zhao, S. Shan, and A. Hauptmann, \u201cSelf-paced curriculum learning,\u201d AAAI, Austin, Texas, USA, pp.2694-1700, AAAI Press, 2015. 10.1609\/aaai.v29i1.9608","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Y. Wan, B. Yang, D.F. Wong, Y. Zhou, L.S. Chao, H. Zhang, and B. Chen, \u201cSelf-paced learning for neural machine translation,\u201d EMNLP, Online, pp.1074-1080, Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.emnlp-main.80","DOI":"10.18653\/v1\/2020.emnlp-main.80"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] D. Ruiter, J. van Genabith, and C. Espa\u00f1a-Bonet, \u201cSelf-induced curriculum learning in self-supervised neural machine translation,\u201d EMNLP, Online, pp.2560-2571, Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.emnlp-main.202","DOI":"10.18653\/v1\/2020.emnlp-main.202"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] T. Sellam, D. Das, and A. Parikh, \u201cBLEURT: Learning robust metrics for text generation,\u201d ACL, Online, pp.7881-7892, Association for Computational Linguistics, July 2020. 10.18653\/v1\/2020.acl-main.704","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] R. Rei, C. Stewart, A.C. Farinha, and A. Lavie, \u201cCOMET: A neural framework for MT evaluation,\u201d EMNLP, Online, pp.2685-2702, Association for Computational Linguistics, Nov. 2020. 10.18653\/v1\/2020.emnlp-main.213","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"23","unstructured":"[23] H. Hassan, A. Aue, C. Chen, V. Chowdhary, J. Clark, C. Federmann, X. Huang, M. Junczys-Dowmunt, W. Lewis, M. Li, et al., \u201cAchieving human parity on automatic chinese to english news translation,\u201d arXiv, vol.abs\/1803.05567, 2018."},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] R. Sennrich, B. Haddow, and A. Birch, \u201cNeural machine translation of rare words with subword units,\u201d ACL, Berlin, German, pp.1715-1725, The Association for Computer Linguistics, 2016. 10.18653\/v1\/p16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"25","unstructured":"[25] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, L. Kaiser, and I. Polosukhin, \u201cAttention is all you need,\u201d NIPS, Red Hook, NY, USA, pp.6000-6010, Curran Associates Inc., 2017."},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] M. Ott, S. Edunov, A. Baevski, A. Fan, S. Gross, N. Ng, D. Grangier, and M. Auli, \u201cfairseq: A fast, extensible toolkit for sequence modeling,\u201d NAACL-HLT, Minneapolis, Minnesota, pp.48-53, Association for Computational Linguistics, 2019. 10.18653\/v1\/n19-4009","DOI":"10.18653\/v1\/N19-4009"},{"key":"27","unstructured":"[27] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d ICLR (Poster), San Diego, CA, USA, OpenReview.net, 2015."},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] K. Papineni, S. Roukos, T. Ward, and W.-J. Zhu, \u201cBleu: a method for automatic evaluation of machine translation,\u201d ACL, Philadelphia, Pennsylvania, USA, pp.311-318, Association for Computational Linguistics, 2002. 10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] M. Collins, P. Koehn, and I. Ku\u010derov\u00e1, \u201cClause restructuring for statistical machine translation,\u201d ACL, Ann Arbor, Michigan, pp.531-540, The Association for Computer Linguistics, 2005. 10.3115\/1219840.1219906","DOI":"10.3115\/1219840.1219906"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] B. Chen and C. Cherry, \u201cA systematic comparison of smoothing techniques for sentence-level bleu,\u201d WMT, Baltimore, Maryland, USA, pp.362-367, Association for Computational Linguistics, 2014. 10.3115\/v1\/w14-3346","DOI":"10.3115\/v1\/W14-3346"},{"key":"31","unstructured":"[31] J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, \u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d NAACL, pp.4171-4186, Association for Computational Linguistics, June 2019."},{"key":"32","unstructured":"[32] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. J\u00e9gou, and T. Mikolov, \u201cFasttext.zip: Compressing text classification models,\u201d arXiv preprint arXiv:1612.03651, 2016."},{"key":"33","unstructured":"[33] K. Duh, \u201cThe multitarget ted talks task.\u201d http:\/\/www.cs.jhu.edu\/~kevinduh\/a\/multitarget-tedtalks\/, 2018."},{"key":"34","unstructured":"[34] J. Gu, J. Bradbury, C. Xiong, V.O.K. Li, and R. Socher, \u201cNon-autoregressive neural machine translation,\u201d ICLR, Vancouver, BC, Canada, OpenReview.net, 2018."},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] D. Wu, L. Ding, F. Lu, and J. Xie, \u201cSlotrefine: A fast non-autoregressive model for joint intent detection and slot filling,\u201d EMNLP, Online, pp.313-319, Association for Computational Linguistics, 2020. 10.18653\/v1\/2020.emnlp-main.152","DOI":"10.18653\/v1\/2020.emnlp-main.152"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] L. Ding, L. Wang, D. Wu, D. Tao, and Z. Tu, \u201cContext-aware cross-attention for non-autoregressive translation,\u201d COLING, Barcelona, Spain (Online), pp.4396-4402, International Committee on Computational Linguistics, 2020. 10.18653\/v1\/2020.coling-main.389","DOI":"10.18653\/v1\/2020.coling-main.389"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/1\/E107.D_2023EDP7048\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T04:14:35Z","timestamp":1704514475000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/1\/E107.D_2023EDP7048\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2023edp7048","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,1]]},"article-number":"2023EDP7048"}}