Improving Arabic Diacritization by Learning to Diacritize and Translate
This work addresses the problem of accurate diacritization for Arabic language processing, which is incremental as it builds on existing methods by incorporating translation tasks.
The paper tackles Arabic diacritization by proposing a multitask learning method that trains a model to both diacritize and translate, leveraging bitext corpora to address data sparsity and improve accuracy, achieving a new state-of-the-art word error rate of 4.79% on the Penn Arabic Treebank.
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%. We also conduct manual and automatic analysis to better understand our method and highlight some of the remaining challenges in diacritization.