Options
Multilingual Machine Translation Systems at WAT 2021: One-to-Many and Many-to-One Transformer based NMT
Journal
WAT 2021 - 8th Workshop on Asian Translation, Proceedings of the Workshop
Date Issued
2021-01-01
Author(s)
Mhaskar, Shivam
Jain, Aditya
Banerjee, Aakash
Bhattacharyya, Pushpak
Abstract
In this paper, we present the details of the systems that we have submitted for the WAT 2021 MultiIndicMT: An Indic Language Multilingual Task. We have submitted two separate multilingual NMT models: one for English to 10 Indic languages and another for 10 Indic languages to English. We discuss the implementation details of two separate multilingual NMT approaches, namely one-to-many and many-to-one, that makes use of a shared decoder and a shared encoder, respectively. From our experiments, we observe that the multilingual NMT systems outperforms the bilingual baseline MT systems for each of the language pairs under consideration.