Low-Resource Language Modelling
Project Showcase

Low-Resource Language Modelling

By: Stuart Mesham , Luc Hayward , Jared Shapiro


About

Abstract

Given a sequence of context words, a language model predicts the next word in the sentence. More formally, a language model assigns a probability to a sequence of words. Modern language models are trained on large datasets, however, many of South Africa’s languages are low resource – there is little text data available for training language models. We evaluate different language models and training methods for modelling South African languages.

Videos 1

Watch presentations, demos, and related content

Documents 1

Downloadable resources and documentation

Click "View Full" to open documents in a new window

Gallery 1

Explore the visual story of this exhibit