Skip to content

Latest commit

 

History

History
19 lines (15 loc) · 709 Bytes

README.md

File metadata and controls

19 lines (15 loc) · 709 Bytes

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}
}