Data Augmentation with Adversarial Training for Cross-Lingual NLI

Xin Dong, Yaxin Zhu, Zuohui Fu, Dongkuan Xu, Gerard de Melo


Abstract
Due to recent pretrained multilingual representation models, it has become feasible to exploit labeled data from one language to train a cross-lingual model that can then be applied to multiple new languages. In practice, however, we still face the problem of scarce labeled data, leading to subpar results. In this paper, we propose a novel data augmentation strategy for better cross-lingual natural language inference by enriching the data to reflect more diversity in a semantically faithful way. To this end, we propose two methods of training a generative model to induce synthesized examples, and then leverage the resulting data using an adversarial training regimen for more robustness. In a series of detailed experiments, we show that this fruitful combination leads to substantial gains in cross-lingual inference.
Anthology ID:
2021.acl-long.401
Volume:
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)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5158–5167
Language:
URL:
https://aclanthology.org/2021.acl-long.401
DOI:
10.18653/v1/2021.acl-long.401
Bibkey:
Cite (ACL):
Xin Dong, Yaxin Zhu, Zuohui Fu, Dongkuan Xu, and Gerard de Melo. 2021. Data Augmentation with Adversarial Training for Cross-Lingual NLI. In 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), pages 5158–5167, Online. Association for Computational Linguistics.
Cite (Informal):
Data Augmentation with Adversarial Training for Cross-Lingual NLI (Dong et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.401.pdf
Video:
 https://aclanthology.org/2021.acl-long.401.mp4