Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach

Víctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez


Abstract
In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the empirical data distribution by generating new sentence pairs that contain infrequent words, thus making it closer to the true data distribution of parallel sentences. In this paper, we propose to follow a completely different approach and present a multi-task DA approach in which we generate new sentence pairs with transformations, such as reversing the order of the target sentence, which produce unfluent target sentences. During training, these augmented sentences are used as auxiliary tasks in a multi-task framework with the aim of providing new contexts where the target prefix is not informative enough to predict the next word. This strengthens the encoder and forces the decoder to pay more attention to the source representations of the encoder. Experiments carried out on six low-resource translation tasks show consistent improvements over the baseline and over DA methods aiming at extending the support of the empirical data distribution. The systems trained with our approach rely more on the source tokens, are more robust against domain shift and suffer less hallucinations.
Anthology ID:
2021.emnlp-main.669
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8502–8516
Language:
URL:
https://aclanthology.org/2021.emnlp-main.669
DOI:
10.18653/v1/2021.emnlp-main.669
Bibkey:
Cite (ACL):
Víctor M. Sánchez-Cartagena, Miquel Esplà-Gomis, Juan Antonio Pérez-Ortiz, and Felipe Sánchez-Martínez. 2021. Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8502–8516, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach (Sánchez-Cartagena et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.669.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.669.mp4
Code
 transducens/mtl-da-emnlp