University of Cape Town

UCT NLP Group

We do research in natural language processing — with a focus on developing language resources and language models for low-resource South African and African languages.

Research Topics

LLMs for low-resource languages

  • Modelling, translation, and generation where data is scarce

Knowledge and linguistic structure in text

  • Knowledge enhancement, segmentation, and meaning representation

South African language data

  • Building NLP datasets and models for multiple languages

Text generation

  • Faithful, controllable generation and evaluation

People

Principal Investigator

Dr. Jan Buys

Co-Investigator

Dr. Francois Meyer

Current postgraduate students

  • Nomonde Khalo (PhD, supervisor Jan Buys)
  • Claytone Sikasote (PhD, supervisor Jan Buys and Hussein Suleman)
  • Natalie Alexander (PhD, supervisor Jan Buys)
  • Anri Lombard (MSc, supervisor Jan Buys, Francois Meyer)
  • Simbarashe Mawere (MSc, supervisor Jan Buys, Francois Meyer)
  • Laura Haworth (MSc, supervisor Jan Buys, Jason Hlozek)
  • Cael Marquard (MSc, supervisor Francois Meyer)
  • Ruba Osman (MSc, supervisor Jan Buys)
  • Razeen Parker (MSc, supervisor Francois Meyer)
  • Sihle Mtwa (PhD, supervisor Salah Kabanda)
  • Prosper Arineitwe Asiimwe (MSc, supervisor Jan Buys, Francois Meyer)

Graduated students

  • Francois Meyer (PhD)
  • Sello Ralethe (PhD)
  • Khalid N. Elmadani (MSc)
  • Natalie Alexander (MSc)
  • Neil Sinclair (MSc)
  • Shane Acton (MSc)
  • Victoria Pedlar (MSc)
  • Yassin Nurmahomed (MSc)
  • Maxwell Mojapelo (MPhil)

Information for prospective students →

Selected Group Publications

Francois Meyer, Haiyue Song, Abhisek Chakrabarty, Jan Buys, Raj Dabre and Hideki Tanaka
LREC-COLING 2024Data

All publications →