Work

Findings of the LoResMT 2020 Shared Task on Zero-Shot for Low-Resource languages

Year: 2020

Type: conference-paper

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 3 rd 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.

DOI: 10.18653/v1/2020.loresmt-1.4

Authors: Atul Kr. Ojha, Valentin Malykh, Alina Karakanta, Chao-Hong Liu

Institutions: Ollscoil na Gaillimhe – University of Galway, Kazan Federal University, University of Trento, Fondazione Bruno Kessler

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funder: Horizon 2020 Framework Programme

Award: G495187929

OpenAlex ID: W3111004703