Transliteration of Judeo-Arabic Texts into Arabic Script Using Recurrent Neural Networks

TL;DR

This paper presents a neural network-based method for transliterating Judeo-Arabic texts into Arabic script, achieving significant error reduction through specialized training techniques and synthetic data generation.

Contribution

The authors develop a recurrent neural network model with CTC loss and pretraining, effectively handling data limitations and context ambiguities in Judeo-Arabic transliteration.

Findings

Achieved 2% character error rate in transliteration

Synthetic data generation improved model performance

Context utilization reduces errors from 2.5% to 2%

Abstract

We trained a model to automatically transliterate Judeo-Arabic texts into Arabic script, enabling Arabic readers to access those writings. We employ a recurrent neural network (RNN), combined with the connectionist temporal classification (CTC) loss to deal with unequal input/output lengths. This obligates adjustments in the training data to avoid input sequences that are shorter than their corresponding outputs. We also utilize a pretraining stage with a different loss function to improve network converge. Since only a single source of parallel text was available for training, we take advantage of the possibility of generating data synthetically. We train a model that has the capability to memorize words in the output language, and that also utilizes context for distinguishing ambiguities in the transliteration. We obtain an improvement over the baseline 9.5% character error, achieving 2% error with our best configuration. To measure the contribution of context to learning, we also tested word-shuffled data, for which the error rises to 2.5%.