Towards Neural Machine Translation for Edoid Languages

TL;DR

This paper investigates the potential of Neural Machine Translation to improve access to information for Edoid languages in Nigeria, using a new dataset and baseline models to promote language technology development.

Contribution

It introduces a new dataset and baseline NMT models for four Edoid languages, facilitating future research in Edoid language translation technology.

Findings

Baseline translation models for Edo, Esan, Urhobo, and Isoko.

Open-sourced datasets, code, and models to support further research.

Demonstrated feasibility of NMT for low-resource Edoid languages.

Abstract

Many Nigerian languages have relinquished their previous prestige and purpose in modern society to English and Nigerian Pidgin. For the millions of L1 speakers of indigenous languages, there are inequalities that manifest themselves as unequal access to information, communications, health care, security as well as attenuated participation in political and civic life. To minimize exclusion and promote socio-linguistic and economic empowerment, this work explores the feasibility of Neural Machine Translation (NMT) for the Edoid language family of Southern Nigeria. Using the new JW300 public dataset, we trained and evaluated baseline translation models for four widely spoken languages in this group: \`Ed\'o, \'Es\'an, Urhobo and Isoko. Trained models, code and datasets have been open-sourced to advance future research efforts on Edoid language technology.