The RGNLP Machine Translation Systems for WAT 2018
This work addresses machine translation challenges for low-resourced Indic languages, but it is incremental as it applies existing methods to a specific shared task.
The paper tackled machine translation for Indic languages in a low-resource setting, achieving the highest scores on automatic metrics for English-to-Telugu, Hindi, Bengali, and Tamil using PBSMT models.
This paper presents the system description of Machine Translation (MT) system(s) for Indic Languages Multilingual Task for the 2018 edition of the WAT Shared Task. In our experiments, we (the RGNLP team) explore both statistical and neural methods across all language pairs. (We further present an extensive comparison of language-related problems for both the approaches in the context of low-resourced settings.) Our PBSMT models were highest score on all automatic evaluation metrics in the English into Telugu, Hindi, Bengali, Tamil portion of the shared task.