Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training

Kuan-Hao Huang, Wasi Ahmad, Nanyun Peng, Kai-Wei Chang


Abstract
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contextual embedding spaces such that even if the representations of different languages are not aligned well, the model can still achieve good performance on zero-shot cross-lingual transfer. In this work, we propose a learning strategy for training robust models by drawing connections between adversarial examples and the failure cases of zero-shot cross-lingual transfer. We adopt two widely used robust training methods, adversarial training and randomized smoothing, to train the desired robust model. The experimental results demonstrate that robust training improves zero-shot cross-lingual transfer on text classification tasks. The improvement is more significant in the generalized cross-lingual transfer setting, where the pair of input sentences belong to two different languages.
Anthology ID:
2021.emnlp-main.126
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1684–1697
Language:
URL:
https://aclanthology.org/2021.emnlp-main.126
DOI:
10.18653/v1/2021.emnlp-main.126
Bibkey:
Cite (ACL):
Kuan-Hao Huang, Wasi Ahmad, Nanyun Peng, and Kai-Wei Chang. 2021. Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1684–1697, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training (Huang et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-main.126.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.emnlp-main.126.mp4
Code
 uclanlp/robust-xlt
Data
PAWS-XXNLI