Language Adapters for Large-Scale MT: The GMU System for the WMT 2022 Large-Scale Machine Translation Evaluation for African Languages Shared Task

Md Mahfuz Ibn Alam, Antonios Anastasopoulos


Abstract
This report describes GMU’s machine translation systems for the WMT22 shared task on large-scale machine translation evaluation for African languages. We participated in the constrained translation track where only the data listed on the shared task page were allowed, including submissions accepted to the Data track. Our approach uses models initialized with DeltaLM, a generic pre-trained multilingual encoder-decoder model, and fine-tuned correspondingly with the allowed data sources. Our best submission incorporates language family and language-specific adapter units; ranking ranked second under the constrained setting.
Anthology ID:
2022.wmt-1.99
Volume:
Proceedings of the Seventh Conference on Machine Translation (WMT)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1015–1033
Language:
URL:
https://aclanthology.org/2022.wmt-1.99
DOI:
Bibkey:
Cite (ACL):
Md Mahfuz Ibn Alam and Antonios Anastasopoulos. 2022. Language Adapters for Large-Scale MT: The GMU System for the WMT 2022 Large-Scale Machine Translation Evaluation for African Languages Shared Task. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 1015–1033, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Language Adapters for Large-Scale MT: The GMU System for the WMT 2022 Large-Scale Machine Translation Evaluation for African Languages Shared Task (Alam & Anastasopoulos, WMT 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2022.wmt-1.99.pdf