Abstract
Unsupervised cross-lingual language representation initialization methods, together with mechanisms such as denoising and back-translation, have advanced unsupervised neural machine translation (UNMT), which has achieved impressive results. Meanwhile, there are still several challenges for UNMT. This tutorial first introduces the background and the latest progress of UNMT. We then examine a number of challenges to UNMT and give empirical results on how well the technology currently holds up1
Cite
CITATION STYLE
Wang, R., & Zhao, H. (2021). Advances and challenges in unsupervised neural machine translation. In EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Tutorial Abstracts (pp. 17–21). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.eacl-tutorials.5
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
