Findings of the Second Shared Task for Creole Language Machine Translation, at WMT 2026

Nathaniel Robinson, Ruth-Ann Armstrong, Claire Bizon Monroc, Rasul Dent, Pranav Gupta, Raj Dabre, Andre Coy, Kenton Murray


Abstract
We present the second annual Shared Task for Creole Language Machine Translation, the only published shared task specializing in machine translation (MT) methods for Creole languages and their communities, presented at the Conference of Machine Translation (WMT) 2026. We accepted system submissions for two tasks: MT and language identification (LID). We received submissions from eight teams: 13 MT systems from six teams across 88 language directions; and four LID systems from two teams, identifying 11 languages each. Our analysis of MT systems indicates fine-tuning with newly curated datasets and/or synthetic data as an effective strategy for producing state-of-the-art MT. For the LID task, we found that smaller, resource-efficient systems achieved state-of-the-art scores on some languages, especially when paired with data augmentation.
Anthology ID:
2026.wmt-main.56
Volume:
Proceedings of the Eleventh Conference on Machine Translation
Month:
October
Year:
2026
Address:
Budapest, Hungary
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venues:
WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1138–1158
Language:
URL:
https://aclanthology.org/2026.wmt-main.56/
DOI:
Bibkey:
Cite (ACL):
Nathaniel Robinson, Ruth-Ann Armstrong, Claire Bizon Monroc, Rasul Dent, Pranav Gupta, Raj Dabre, Andre Coy, and Kenton Murray. 2026. Findings of the Second Shared Task for Creole Language Machine Translation, at WMT 2026. In Proceedings of the Eleventh Conference on Machine Translation, pages 1138–1158, Budapest, Hungary. Association for Computational Linguistics.
Cite (Informal):
Findings of the Second Shared Task for Creole Language Machine Translation, at WMT 2026 (Robinson et al., WMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.wmt-main.56.pdf