metadata
title: README
emoji: 📊
colorFrom: blue
colorTo: purple
sdk: static
pinned: false
Digital Techniques for Language Revival
We explore how technology can support comparative linguistics, language education, and the revitalisation and revival of languages.
Aims
- NMT model training
- Corpus building
- Bridging pedagogy and typology
Current Study: Sentence-Level Corpus for Arem
Our current study focuses on documenting the critically endangered Arem language. We are developing a smartphone app to record sentences and support fieldwork to build a parallel corpus in English, Vietnamese, and Arem. By collecting language at the sentence level, the project aims to capture context and usage beyond word lists alone.
The resulting corpus will support research into Arem grammar, the creation of a dictionary with example sentences showing how words are used, and the development of neural machine translation models.