Welcome to the GitHub repository for my Bachelor's thesis on bilingual lexicon induction for Oshiwambo. This repository contains the code for the experiments.
The thesis itself will be available soon.
Details on how to reproduce the experiments are provided in the experiments directory.
Note that due to copyright issues, no data is provided in this repository. The Swahili experiments can easily be reproduced by crawling your own corpus using the provided scripts. The seeds can be generated using Google Translate.
If you need access to the rest of the data, please contact me at via email.