The University of Maryland, College Park Submission to Large-Scale Multilingual Shared Task at WMT 2021

Saptarashmi Bandyopadhyay, Tasnim Kabir, Zizhen Lian, Marine Carpuat


Abstract
This paper describes the system submitted to Large-Scale Multilingual Shared Task (Small Task #2) at WMT 2021. It is based on the massively multilingual open-source model FLORES101_MM100 model, with selective fine-tuning.Our best-performing system reported a 15.72 average BLEU score for the task.
Anthology ID:
2021.wmt-1.46
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venue:
WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
383–386
Language:
URL:
https://aclanthology.org/2021.wmt-1.46
DOI:
Bibkey:
Cite (ACL):
Saptarashmi Bandyopadhyay, Tasnim Kabir, Zizhen Lian, and Marine Carpuat. 2021. The University of Maryland, College Park Submission to Large-Scale Multilingual Shared Task at WMT 2021. In Proceedings of the Sixth Conference on Machine Translation, pages 383–386, Online. Association for Computational Linguistics.
Cite (Informal):
The University of Maryland, College Park Submission to Large-Scale Multilingual Shared Task at WMT 2021 (Bandyopadhyay et al., WMT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.wmt-1.46.pdf
Data
CCAlignedFLORES-101