Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation

Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Weihua Luo, Rong Jin


Abstract
The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, and thus produce a model capable of generalizing to unseen instances. However, it is commonly observed that the generalization performance of the model is highly influenced by the amount of parallel data used in training. Although data augmentation is widely used to enrich the training data, conventional methods with discrete manipulations fail to generate diverse and faithful training samples. In this paper, we present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT), which augments each training instance with an adjacency semantic region that could cover adequate variants of literal expression under the same meaning. We conduct extensive experiments on both rich-resource and low-resource settings involving various language pairs, including WMT14 English{German,French}, NIST ChineseEnglish and multiple low-resource IWSLT translation tasks. The provided empirical evidences show that CsaNMT sets a new level of performance among existing augmentation techniques, improving on the state-of-the-art by a large margin. The core codes are contained in Appendix E.
Anthology ID:
2022.acl-long.546
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7930–7944
Language:
URL:
https://aclanthology.org/2022.acl-long.546
DOI:
10.18653/v1/2022.acl-long.546
Award:
 Outstanding Paper
Bibkey:
Cite (ACL):
Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Weihua Luo, and Rong Jin. 2022. Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7930–7944, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation (Wei et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.546.pdf
Video:
 https://aclanthology.org/2022.acl-long.546.mp4
Code
 pemywei/csanmt +  additional community code