All projects
AI & ComputingOngoingCollaborative

Adaptive Language Models for Low-Resource Tongues

Building parameter-efficient transformer architectures that learn from fewer than ten thousand sentences, extending modern NLP to languages historically excluded from the digital record.

PI · Dr. Anita RaoDr. Anita Rao, M. Okafor, L. Bianchi

Objectives

  • Curate aligned corpora for eight under-resourced languages
  • Benchmark adapter-based fine-tuning against full fine-tuning
  • Release an open evaluation suite for morphological richness

Methodology

A mixed pipeline of community-sourced annotation and self-supervised pretraining, evaluated through held-out translation and cloze tasks with native-speaker review panels.

Current status

64%