Au sujet de ce document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Mikel Artetxe
- sl:arxiv_num : 2004.14958
- sl:arxiv_published : 2020-04-30T17:06:23Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : A Call for More Rigor in Unsupervised Cross-lingual Learning@en
- sl:arxiv_updated : 2020-04-30T17:06:23Z
- sl:bookmarkOf : https://arxiv.org/abs/2004.14958
- sl:creationDate : 2020-05-02
- sl:creationTime : 2020-05-02T12:35:54Z
Documents with similar tags (experimental)
Préférences...