A Comparative Study of SMT and NMT: Case Study of English-Nepali Language Pair
August 2018
Abstract
Machine Translation is one of the major problems in the field of Natural Language Processing. In due course, many approaches have been applied in order to solve this problem ranging from the traditional rule-based approach, statistical methods to the more recent neural network based methods. Neural network based methods have produced comparable results to that of the existing phrase based model and in some language pairs they have even outperformed the latter. A huge amount of parallel corpus is required for both the SMT and NMT models in order to produce reasonable results. For some language pairs, the required data is readily available but for many others it is not necessarily the case. This research work focuses on the comparative study of how SMT and NMT based machine translation models perform and compare to each other in case where the language pair is under resourced in terms of the availability of the parallel corpus.