Exploring System Combination approaches for Indo-Aryan MT Systems

Statistical Machine Translation (SMT) systems are heavily dependent on the quality of parallel corpora used to train translation models. Translation quality between certain Indian languages is often poor due to the lack of training data of good quality. We used triangulation as a technique to improve the quality of translations in cases where the direct translation model did not perform satisfactorily. Triangulation uses a third language as a pivot between the source and target languages to achieve an improved and more efficient translation model in most cases. We also combined multi-pivot models using linear mixture and obtained significant improvement in BLEU scores compared to the direct source-target models.