A Call for More Rigor in Unsupervised Cross-lingual Learning

Mikel Artetxe, Sebastian Ruder, Dani Yogatama, Gorka Labaka, Eneko Agirre


Abstract
We review motivations, definition, approaches, and methodology for unsupervised cross-lingual learning and call for a more rigorous position in each of them. An existing rationale for such research is based on the lack of parallel data for many of the world’s languages. However, we argue that a scenario without any parallel data and abundant monolingual data is unrealistic in practice. We also discuss different training signals that have been used in previous work, which depart from the pure unsupervised setting. We then describe common methodological issues in tuning and evaluation of unsupervised cross-lingual models and present best practices. Finally, we provide a unified outlook for different types of research in this area (i.e., cross-lingual word embeddings, deep multilingual pretraining, and unsupervised machine translation) and argue for comparable evaluation of these models.
Anthology ID:
2020.acl-main.658
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7375–7388
Language:
URL:
https://aclanthology.org/2020.acl-main.658
DOI:
10.18653/v1/2020.acl-main.658
Bibkey:
Cite (ACL):
Mikel Artetxe, Sebastian Ruder, Dani Yogatama, Gorka Labaka, and Eneko Agirre. 2020. A Call for More Rigor in Unsupervised Cross-lingual Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7375–7388, Online. Association for Computational Linguistics.
Cite (Informal):
A Call for More Rigor in Unsupervised Cross-lingual Learning (Artetxe et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.658.pdf
Video:
 http://slideslive.com/38929161
Data
GLUEMLDocXNLI