Researching Language Preservation
Nesdia is a research initiative exploring new methodologies for safeguarding and revitalizing endangered languages through computational linguistics and AI.
Core Pillars
Language Documentation
Investigating methods for preserving endangered and historical languages through structured digital archives, ensuring cultural heritage remains accessible for scholarship and revitalization efforts led by descendant communities.
Source Materials
Developing techniques for high-resolution digitization of fragile manuscripts and texts, transforming physical artifacts into structured, machine-readable corpora for computational analysis and cross-linguistic study.
Computational Tools
Exploring modern NLP applications for linguistic analysis , including morphological parsing, lexical semantic change detection, and cross-lingual transfer learning, accelerating work that traditionally required decades of manual effort.
Curated Datasets
Building annotated linguistic datasets structured for academic research: transcribed speech corpora, morphologically tagged texts, and parallel translations for low-resource language pairs.
Empower Scholars
Prototyping tools for linguists, field researchers, and cultural institutions to transform archival materials into searchable, analyzable resources for active scholarship.
Scholarly Rigour
Human expertise at the core. Computational tools accelerate discovery, but every annotation, transcription, and reconstruction undergoes expert review. We assist documentation; we do not replace the linguist.
From Fragments to Analysis
Our research begins with the last remaining traces of vulnerable languages, from historical manuscripts and fragmented texts to modern field recordings. We are developing methods to digitize and collate this precious data, creating a foundational archive for analysis.
Our Computational Pipeline
The long-term goal of our research is a living, structured archive. We envision researchers, descendant communities, and the world gaining unprecedented access to study and engage with the rich heritage of these languages.
A Living Archive for the World
The long-term goal of our research is a living, structured archive. We envision researchers, descendant communities, and the world gaining unprecedented access to study and engage with the rich heritage of these languages.
A Lifeline for Endangered Languages
“This work is of immense importance for the preservation of endangered languages and cultures.”
