Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi

TL;DR

This paper details the development of linguistic resources and a machine translation model for Gondi, a low-resource language, using innovative data collection and compression techniques to enhance digital access and community engagement.

Contribution

It introduces a scalable data collection method, a compressed machine translation model, and community engagement strategies for Gondi, a low-resource language.

Findings

Created a 26,240 translation corpus for Gondi.

Developed a compressed Hindi-Gondi translation model suitable for edge devices.

Engaged 850 community members in language digitalization efforts.

Abstract

The primary obstacle to developing technologies for low-resource languages is the lack of representative, usable data. In this paper, we report the deployment of technology-driven data collection methods for creating a corpus of more than 60,000 translations from Hindi to Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. During this process, we help expand information access in Gondi across 2 different dimensions (a) The creation of linguistic resources that can be used by the community, such as a dictionary, children's stories, Gondi translations from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform; (b) Enabling its use in the digital domain by developing a Hindi-Gondi machine translation model, which is compressed by nearly 4 times to enable it's edge deployment on low-resource edge devices and in areas of little to no internet connectivity. We also present preliminary evaluations of utilizing the developed machine translation model to provide assistance to volunteers who are involved in collecting more data for the target language. Through these interventions, we not only created a refined and evaluated corpus of 26,240 Hindi-Gondi translations that was used for building the translation model but also engaged nearly 850 community members who can help take Gondi onto the internet.