Language technology for the Uralic languages in an Amazonian context
Year: 2025
Type: article
Abstract: This article explores the application of language technology developed for Uralic languages in the revitalization, invigoration and research of Indigenous Amazonian languages. It highlights the potential and challenges of digital tool development for linguistically and culturally rich languages with minimal resources. Uralic language technology derives from the facilitation of Saami languages and over 150 other languages world-wide, including Indigenous Amazonian languages, such as Apurinã and Sakurabiat, in the GiellaLT infrastructure. This language-independent framework has been established, emphasizing reusability of technology and code to address the virtual lack of digital resources for minority languages, which helps in the enhancement of language documentation, education, and revitalization efforts. The authors present collaborative work between European and Brazilian researchers, emphasizing the importance of co-design with native speaker communities to ensure tools, such as spellcheckers, morphological analyzers, and keyboards, reflect actual language use. It is noted that despite environmental and cultural differences between Northern Eurasia and the Amazon, both regions share common challenges, such as underused language archives and endangered language vitality. The research underscores the importance of cross-regional cooperation and open-source, modular infrastructures for advancing language technology in minority and endangered language contexts worldwide.
Source: Työväentutkimus Vuosikirja
Authors: Rueter, Jack, Partanen, Niko
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: green
OpenAlex ID: W7199402520