January 1, 2021Open Access

Language Tags Matter for Zero-Shot Neural Machine Translation

Key Points

Key points are not available for this paper at this time.

Abstract

Multilingual Neural Machine Translation (MNMT) has aroused widespread interest due to its efficiency. An exciting advantage of MNMT models is that they could also translate between unsupervised (zero-shot) language directions.

Bookmark

View Full Paper

Cite This Study

Wu et al. (Fri,) studied this question.

synapsesocial.com/papers/6a1bd5fc00ee29383e9d01bd https://doi.org/https://doi.org/10.18653/v1/2021.findings-acl.264

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Language-aware Interlingua for Multilingual Neural Machine Translation2020 · 35 citations
2Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation2020 · 82 citations
3Visualizing Data using t-SNE2008 · 35,732 citations
4Multilingual neural machine translation with soft decoupled encoding2019 · 42 citations
5Convolutional Sequence to Sequence Learning2017 · 1,340 citations

Bookmark

View Full Paper