Findings of the LoResMT 2020 shared task on zero-shot for low-resource languages

Ojha, Atul Kr., Malykh, Valentin, Karakanta, Alina, & Liu, Chao-Hong. (2020). Findings of the LoResMT 2020 shared task on zero-shot for low-resource languages. Paper presented at the 3rd Workshop on Technologies for MT of Low Resource Languages, Suzhou, China, 04 December.

Abstract

This paper presents the findings of the LoResMT 2020 Shared Task on zero-shot translation for low resource languages. This task was organised as part of the 3rd Workshop on Technologies for MT of Low Resource Languages (LoResMT) at AACL-IJCNLP 2020. The focus was on the zero-shot approach as a notable development in Neural Machine Translation to build MT systems for language pairs where parallel corpora are small or even nonexistent. The shared task experience suggests that back-translation and domain adaptation methods result in better accuracy for smallsize datasets. We further noted that, although translation between similar languages is no cakewalk, linguistically distinct languages require more data to give better results.

Funder

Horizon 2020

Publisher

Association for Computational Linguistics

Rights

Attribution-NonCommercial-NoDerivs 3.0 Ireland

cbn

Collections

Data Science Institute (Conference Papers)