Improving Arabic Diacritization by Learning to Diacritize and Translate

09/29/2021

∙

by   Brian Thompson, et al.

∙

0

∙

share

We propose a novel multitask learning method for diacritization which trains a model to both diacritize and translate. Our method addresses data sparsity by exploiting large, readily available bitext corpora. Furthermore, translation requires implicit linguistic and semantic knowledge, which is helpful for resolving ambiguities in the diacritization task. We apply our method to the Penn Arabic Treebank and report a new state-of-the-art word error rate of 4.79 method and highlight some of the remaining challenges in diacritization.