Creating Resources for Under-Represented Languages: Hakha Chin

Dear LINGUIST List readers and subscribers,

The theme for this year’s Fund Drive is Language Documentation and Revitalization, because of this year’s theme, I would like to tell you about some of the work that I am involved with at Indiana University in addition to working at The LINGUIST List. I am a Computational Linguistics PhD student here at and as part of my work as a graduate student I am involved with a language documentation project: building documentary materials and computational tools for Hakha Chin. It should be noted that The LINGUIST List is not affiliated with this project, rather it is work that I am doing as a student while also working at The LINGUIST List.

Hakha Chin (Laiholh) is a language spoken in Myanmar/Burma with roughly 165,000 speakers, and there are more than 23,000 Burmese refugees who call Indiana home with nearly 17,000 residing in Indianapolis. Last year Hakha Chin was the language that was studied in the field methods classes taught by Dr. Kelly Berkson. Since there are not many resources available for Hakha Chin, the motivation behind this project is simple: having access to information in your native language is not a privilege, but a right. This motivation has lead to projects like using Mozilla Common Voice for Hakha Chin.

This is a screenshot of the Common Voice homepage illustrating the idea behind their system.

Mozilla Common Voice is a project whose aim is to “help make voice recognition open and accessible to everyone”. They do this by having users donate their voice and by listening to validate other submissions. Follow this link to see the page for Hakha Chin.

Here is a screenshot of what Common Voice looks like for Hakha Chin.

The Hakha Chin Common Voice Project has gotten very popular among the Hakha Chin speaking community. Mentions of this project have appeared on the Travel Myanmar YouTube channel and on the Chin Cable Network. Below you can see our very own Dr. Berkson discussing the work that is being done with Hakha Chin on the Travel Myanmar YouTube channel.

There is a lot of work revolving around Hakha Chin at IU at the moment, and there are multiple graduate students, myself included, working on this language. For example, I am working on creating a Universal Dependencies treebank so that I can work on Dependency Parsing for Hakha Chin.

To see some other cool things that are happening in the world of Language Revitalization and Documentation be sure to check back on our blog and social media pages, but most importantly, visit our Fund Drive page – it is here where you can learn more about us and make a donation. Thank you for your continued support.

Sincerely,

Becca Morris, on behalf of The LINGUIST List Team

(Sources: https://www.ethnologue.com/language/cnh, https://thebaci.org/)

Leave a Reply