The Impact of Preprocessing on Arabic-English Statistical and Neural Machine Translation
This work addresses the optimization of machine translation systems for Arabic-English, which is incremental as it builds on existing tokenization techniques by comparing them across different models and data sizes.
The paper tackled the problem of how preprocessing, specifically tokenization schemes, affects Arabic-English machine translation performance for both statistical and neural models, finding that the best tokenization depends on model type and data size, and that combining outputs from both models yields significant improvements, with concrete gains reported.
Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While linguistically-motivated tokenization techniques were shown to have significant effects on the performance of statistical MT, it remains unclear if those techniques are well suited for neural MT. In this paper, we systematically compare neural and statistical MT models for Arabic-English translation on data preprecossed by various prominent tokenization schemes. Furthermore, we consider a range of data and vocabulary sizes and compare their effect on both approaches. Our empirical results show that the best choice of tokenization scheme is largely based on the type of model and the size of data. We also show that we can gain significant improvements using a system selection that combines the output from neural and statistical MT.