Natural Language Processing

Compositional Instruction Following with Language Models and Reinforcement Learning
Combining reinforcement learning with language grounding is challenging as the agent needs to explore the environment while …
PDF Cite Project
The Zeno’s Paradox of ‘Low-Resource’ Languages
The disparity in the languages commonly studied in Natural Language Processing (NLP) is typically reflected by referring to languages …
PDF Cite
Preparing the Vuk'uzenzele and ZA-gov-multilingual South African Multilingual Corpora
This paper introduces two multilingual government themed corpora in various South African languages. The corpora were collected by …
PDF Cite
End-to-End Learning to Follow Language Instructions with Compositional Policies
We develop an end-to-end model for learning to follow language instructions with compositional policies. Our model combines large …
PDF Cite Project
Participatory Translations of Oshiwambo: Towards Culture Preservation with Language Technology
In this paper, we describe a participatory, collaborative, and cost-effective process for creating translations in Oshiwambo, the most …
PDF Cite
Analysing the Effects of Transfer Learning on Low-Resourced Named Entity Recognition Performance
Transfer learning has led to large gains in performance for nearly all NLP tasks while making downstream models easier and faster to …
PDF Cite
Effect of Tokenisation Strategies for Low-Resourced Southern African Languages
Research into machine translation for African languages is very limited and low- resourced in terms of datasets and model evaluations. …
PDF Cite
Learning to Follow Language Instructions with Compositional Policies
We propose a framework that learns to execute natural language instructions in an environment consisting of goal-reaching tasks that …
PDF Cite Project
Implementation of a Neural Natural Language Understanding Component for Arabic Dialogue Systems
Natural Language Understanding (NLU) is considered a core component in implementing dialogue systems. NLU has been greatly enhanced by …
PDF Cite