Improving Arabic Diacritization by Learning to Diacritize and Translate

TL;DR

This paper introduces a multitask learning approach that jointly diacritizes and translates Arabic, leveraging large bitext corpora to improve accuracy and address data sparsity, achieving state-of-the-art results.

Contribution

It presents a novel multitask model that combines diacritization and translation, exploiting translation data to enhance diacritization performance.

Findings

Achieved a new state-of-the-art word error rate of 4.79%.

Demonstrated the effectiveness of multitask learning for Arabic diacritization.

Provided analysis of remaining challenges in diacritization.

Abstract

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.