CLDec 28, 2024Code
YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá TextAkindele Michael Olawole, Jesujoba O. Alabi, Aderonke Busayo Sakpere et al.
In this work, we present Yorùbá automatic diacritization (YAD) benchmark dataset for evaluating Yorùbá diacritization systems. In addition, we pre-train text-to-text transformer, T5 model for Yorùbá and showed that this model outperform several multilingually trained T5 models. Lastly, we showed that more data and larger models are better at diacritization for Yorùbá