Yoruba Embeddings for NLP
# The Challenge of Diacritics in Yorùbá Embeddings
NOTE:
This paper was accepted for presentation at NeurIPS 2020 ML4D Workshop
License:
All codes, data and models are released under CCBY 4.0. The word2vec embedding from the undiacritized Wiki data can be downloaded here .
How do I cite?
Please cite the NeurIPS 2020 ML4D paper:
@article{adewumi2020challenge,
title={The Challenge of Diacritics in Yoruba Embeddings},
author={Adewumi, Tosin P and Liwicki, Foteini and Liwicki, Marcus},
journal={arXiv preprint arXiv:2011.07605},
year={2020}
}