Performance Comparison of Statistical vs. Neural-Based Translation System on Low-Resource Languages

One of the important applications for which natural language processing (NLP) is used is the machine translation (MT) system, which automatically converts one natural language to another. It has witnessed various paradigm shifts since its inception. Statistical machine translation (SMT) has dominated MT research for decades. In the recent past, researchers have focused on developing MT systems based on artificial neural networks (ANN). In this paper, first, some important deep learning models that are mostly exploited in Neural Machine Translation (NMT) design are discussed. A systematic comparison was done between the performances of SMT and NMT concerning the English-to-Bangla and English-to-Hindi translation tasks. Most of the Indian scripts are morphologically rich, and the availability of a sufficient corpus is rare. We have presented and analyzed our work and a survey was conducted on other low-resource languages, and finally some useful conclusions have been drawn.