Multilingual Machine Translation Systems at WAT 2021: One-to-Many and Many-to-One Transformer based NMT

Shivam Mhaskar, Aditya Jain, Aakash Banerjee, Pushpak Bhattacharyya


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.
Anthology ID:
2021.wat-1.28
Volume:
Proceedings of the 8th Workshop on Asian Translation (WAT2021)
Month:
August
Year:
2021
Address:
Online
Editors:
Toshiaki Nakazawa, Hideki Nakayama, Isao Goto, Hideya Mino, Chenchen Ding, Raj Dabre, Anoop Kunchukuttan, Shohei Higashiyama, Hiroshi Manabe, Win Pa Pa, Shantipriya Parida, Ondřej Bojar, Chenhui Chu, Akiko Eriguchi, Kaori Abe, Yusuke Oda, Katsuhito Sudoh, Sadao Kurohashi, Pushpak Bhattacharyya
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
233–237
Language:
URL:
https://aclanthology.org/2021.wat-1.28
DOI:
10.18653/v1/2021.wat-1.28
Bibkey:
Cite (ACL):
Shivam Mhaskar, Aditya Jain, Aakash Banerjee, and Pushpak Bhattacharyya. 2021. Multilingual Machine Translation Systems at WAT 2021: One-to-Many and Many-to-One Transformer based NMT. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 233–237, Online. Association for Computational Linguistics.
Cite (Informal):
Multilingual Machine Translation Systems at WAT 2021: One-to-Many and Many-to-One Transformer based NMT (Mhaskar et al., WAT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wat-1.28.pdf