UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP

M Saiful Bari, Tasnim Mohiuddin, Shafiq Joty


Abstract
Transfer learning has yielded state-of-the-art (SoTA) results in many supervised NLP tasks. However, annotated data for every target task in every target language is rare, especially for low-resource languages. We propose UXLA, a novel unsupervised data augmentation framework for zero-resource transfer learning scenarios. In particular, UXLA aims to solve cross-lingual adaptation problems from a source language task distribution to an unknown target language task distribution, assuming no training label in the target language. At its core, UXLA performs simultaneous self-training with data augmentation and unsupervised sample selection. To show its effectiveness, we conduct extensive experiments on three diverse zero-resource cross-lingual transfer tasks. UXLA achieves SoTA results in all the tasks, outperforming the baselines by a good margin. With an in-depth framework dissection, we demonstrate the cumulative contributions of different components to its success.
Anthology ID:
2021.acl-long.154
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
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1978–1992
Language:
URL:
https://aclanthology.org/2021.acl-long.154
DOI:
10.18653/v1/2021.acl-long.154
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.154.pdf
Data
PAWS-XXNLI