JU-saarland submission in the WMT2019 English-Gujarati translation shared task

Abstract

In this paper we describe our joint submission (JU-Saarland) from Jadavpur University and Saarland University in the WMT 2019 news translation shared task for English-Gujarati language pair within the translation task sub-track. Our baseline and primary submissions are built using a Recurrent neural network (RNN) based neural machine translation (NMT) system which follows attention mechanism followed by fine-tuning using in-domain data. Given the fact that the two languages belong to different language families and there is not enough parallel data for this language pair, building a high quality NMT system for this language pair is a difficult task. We produced synthetic data through back-translation from available monolingual data. We report the automatic evaluation scores of our English-Gujarati and Gujarati-English NMT systems trained at word, byte-pair and character encoding levels where RNN at word level is considered as the baseline and used for comparison purpose. Our English-Gujarati system ranked in the second position in the shared task.