Towards Sinhala Tamil machine translation

Statistical Machine Translation is a well established data-driven approach to translate source language text to target language text using statistical methods using bilingually aligned corpora. However there has been little research in this area for less well-resourced languages such as Sinhala and Tamil. The focus of this research is to investigate how translation performance varies with the amount of parallel training data in order to find out the minimum needed to develop a baseline machine translation system for the Sinhala-Tamil language pair.