JUST System for WMT20 Chat Translation Task

Roweida Mohammed, Mahmoud Al-Ayyoub, Malak Abdullah


Abstract
Machine Translation (MT) is a sub-field of Artificial Intelligence and Natural Language Processing that investigates and studies the ways of automatically translating a text from one language to another. In this paper, we present the details of our submission to the WMT20 Chat Translation Task, which consists of two language directions, English –> German and German –> English. The major feature of our system is applying a pre-trained BERT embedding with a bidirectional recurrent neural network. Our system ensembles three models, each with different hyperparameters. Despite being trained on a very small corpus, our model produces surprisingly good results.
Anthology ID:
2020.wmt-1.59
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Editors:
Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
479–482
Language:
URL:
https://aclanthology.org/2020.wmt-1.59
DOI:
Bibkey:
Cite (ACL):
Roweida Mohammed, Mahmoud Al-Ayyoub, and Malak Abdullah. 2020. JUST System for WMT20 Chat Translation Task. In Proceedings of the Fifth Conference on Machine Translation, pages 479–482, Online. Association for Computational Linguistics.
Cite (Informal):
JUST System for WMT20 Chat Translation Task (Mohammed et al., WMT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wmt-1.59.pdf
Video:
 https://slideslive.com/38939629