Options
Language Relatedness and Lexical Closeness can help Improve Multilingual NMT: IITBombay@MultiIndicNMT WAT2021
Journal
WAT 2021 - 8th Workshop on Asian Translation, Proceedings of the Workshop
Date Issued
2021-01-01
Author(s)
Khatri, Jyotsana
Saini, Nikhil
Bhattacharyya, Pushpak
Abstract
Multilingual Neural Machine Translation has achieved remarkable performance by training a single translation model for multiple languages. This paper describes our submission (Team ID: CFILT-IITB) for the MultiIndicMT: An Indic Language Multilingual Task at WAT 2021. We train multilingual NMT systems by sharing encoder and decoder parameters with language embedding associated with each token in both encoder and decoder. Furthermore, we demonstrate the use of transliteration (script conversion) for Indic languages in reducing the lexical gap for training a multilingual NMT system. Further, we show improvement in performance by training a multilingual NMT system using languages of the same family, i.e., related languages.