Collaborative Research: Advancing Indigenous Language Technologies

Many languages are endangered, including numerous Indigenous languages. Because endangered languages have strong linguistic and cultural significance, as well as scientific value as a component of linguistic infrastructure, it is important to support and inform documentation and revitalization efforts for these languages. Modern technologies, including infrastructure to archive large-scale collections of recordings and computer-based analysis tools, have strong potential to facilitate documentation efforts.

However, not all stakeholders have access to these technologies. This project advances knowledge concerning the necessary training and resources required to support effective and inclusive use of technology in the context of endangered Indigenous languages. This work is timely because many language communities are faced with urgent needs to develop language technology to support documentation efforts.

This project provides education for students and community members. It also benefits society by expanding language technology development to include Indigenous language community members, a significantly underserved population.

Sustainable language technology development must be consistent with the needs, practices, and values of the communities undertaking the work, and, in many cases, is best done within the communities themselves. This community-based project addresses problems that stem from difficulties in access to technology infrastructure in Indigenous communities and linguistic biases built into existing computational technologies.

In doing so, it incorporates communities' needs, practices, and values regarding data sovereignty and appropriate access to language materials. Using a multidisciplinary and multi-institutional approach, the project builds capacity and infrastructure to support the development of effective, durable, and appropriate language related technologies by Indigenous communities.

The project creates a network of diverse individuals who share expertise, resources, and tools for capacity development in addition to resources needed to create and maintain language-related technologies (e.g., applications, websites, keyboard inputs, dictionaries) and natural language processing and AI technologies (e.g., speech-to-text, text-to-speech, predictive text, machine translation). This project yields a sustainable set of technological supports that integrate with community values and advance ongoing Indigenous language revitalization.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.