Linguistic Divergence of Sinhala and Tamil Languages in Machine Translation

This paper presents a study of the lexical-semantic divergence between Sinhala and Tamil languages. Study of divergence is critical as differences in linguistic and extra-linguistic features in languages play pivotal roles in translation. This research the first study of the divergence between Sinhala and Tamil languages and is based on Dorr's classification. We propose a computer-assisted divergence study procedure using statistical machine translation, which is easy and gives good performance compared to traditional approaches. Accordingly, this research has the twin aims of revisiting classification of divergence types as outlined by Dorr and outlining some of the new divergence patterns specific to Sinhala and Tamil languages. This study proposes a rule-based algorithm to classify a divergence.