Harnessing the Power of Artificial Intelligence to Vitalize Endangered Indigenous Languages: Technologies and Experiences

TL;DR

This work tackles the challenge of sustaining endangered Indigenous languages by deploying AI/NLP under a community-centered, sovereignty-based framework. It introduces a practical AI development cycle anchored in community usage, and demonstrates that ultra-low-resource fine-tuning of high-resource translators can yield useful writing tools and translators for Guarani Mbya and Nheengatu. It also articulates the concepts of Indigenous Language Models (ILMs) and Endangered Language Tools (ELTs) as scalable, replicable avenues for writing assistants and interactive language documentation, while emphasizing data quality and governance to avoid contamination. The study provides concrete, co-designed teaching and tooling experiences in Brazilian Indigenous communities, and argues for smartphone-enabled deployment and participatory governance to sustain language vitality. Collectively, the work lays a blueprint for ethically, effectively preserving and revitalizing Indigenous languages through community-guided AI tooling that can be replicated across communities and languages.

Abstract

Since 2022 we have been exploring application areas and technologies in which Artificial Intelligence (AI) and modern Natural Language Processing (NLP), such as Large Language Models (LLMs), can be employed to foster the usage and facilitate the documentation of Indigenous languages which are in danger of disappearing. We start by discussing the decreasing diversity of languages in the world and how working with Indigenous languages poses unique ethical challenges for AI and NLP. To address those challenges, we propose an alternative development AI cycle based on community engagement and usage. Then, we report encouraging results in the development of high-quality machine learning translators for Indigenous languages by fine-tuning state-of-the-art (SOTA) translators with tiny amounts of data and discuss how to avoid some common pitfalls in the process. We also present prototypes we have built in projects done in 2023 and 2024 with Indigenous communities in Brazil, aimed at facilitating writing, and discuss the development of Indigenous Language Models (ILMs) as a replicable and scalable way to create spell-checkers, next-word predictors, and similar tools. Finally, we discuss how we envision a future for language documentation where dying languages are preserved as interactive language models.

Figures (15)

• Figure 1: Histograms of 444 Indigenous languages used in the Americas today and of 221 Indigenous languages in Brazil (based on 2010 numbers) with the number of languages for different logarithmic intervals of number of speakers.
• Figure 2: Histograms of the number of Brazilian Indigenous languages with a descriptive page in Wikipedia per number of speakers (left) and according to different levels of endangerment (right).
• Figure 3: Photographs taken during the workshops at the Gwyra Pepo Indigenous High School in 2023.
• Figure 4: Traditional AI development cycle (a) and the proposed AI development cycle for Indigenous communities with emphasis on community usage, engagement, and sovereignty (b).
• Figure 5: Average and standard deviation scores in different test sets of languages for the fine-tuning of mBART50 and WMT19 to different models for each of the three metrics. The best models of each group are indicated with the bold typeface.