Transliteration of Judeo-Arabic Texts into Arabic Script Using Recurrent Neural Networks
This enables Arabic readers to access Judeo-Arabic writings, but it is incremental as it applies existing methods to a new domain-specific dataset.
The researchers tackled the problem of automatically transliterating Judeo-Arabic texts into Arabic script using a recurrent neural network with CTC loss and synthetic data generation, achieving a character error rate of 2% compared to a baseline of 9.5%.
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%.