Transfer Learning for Related Languages: Submissions to the WMT20 Similar Language Translation Task

Lovish Madaan, Soumya Sharma, Parag Singla


Abstract
In this paper, we describe IIT Delhi’s submissions to the WMT 2020 task on Similar Language Translation for four language directions: Hindi <-> Marathi and Spanish <-> Portuguese. We try out three different model settings for the translation task and select our primary and contrastive submissions on the basis of performance of these three models. For our best submissions, we fine-tune the mBART model on the parallel data provided for the task. The pre-training is done using self-supervised objectives on a large amount of monolingual data for many languages. Overall, our models are ranked in the top four of all systems for the submitted language pairs, with first rank in Spanish -> Portuguese.
Anthology ID:
2020.wmt-1.46
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
402–408
Language:
URL:
https://aclanthology.org/2020.wmt-1.46
DOI:
Bibkey:
Cite (ACL):
Lovish Madaan, Soumya Sharma, and Parag Singla. 2020. Transfer Learning for Related Languages: Submissions to the WMT20 Similar Language Translation Task. In Proceedings of the Fifth Conference on Machine Translation, pages 402–408, Online. Association for Computational Linguistics.
Cite (Informal):
Transfer Learning for Related Languages: Submissions to the WMT20 Similar Language Translation Task (Madaan et al., WMT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.wmt-1.46.pdf
Video:
 https://slideslive.com/38939620