UXLA: A robust unsupervised data augmentation framework for zero-resource cross-lingual NLP

M. Saiful Bari*, Tasnim Mohiuddin*, Shafiq Joty

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages1978-1992
Number of pages15
ISBN (Electronic)9781954085527
Publication statusPublished - 2021
Externally publishedYes
EventJoint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 - Virtual, Online
Duration: 1 Aug 20216 Aug 2021

Publication series

NameACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference

Conference

ConferenceJoint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
CityVirtual, Online
Period1/08/216/08/21

Fingerprint

Dive into the research topics of 'UXLA: A robust unsupervised data augmentation framework for zero-resource cross-lingual NLP'. Together they form a unique fingerprint.

Cite this