UoM-DFKI submission to the low resource shared task

Kumar Rishu, Aiden Williams, Claudia Borg, Simon Ostermann


Abstract
This system description paper presents the details of our primary and contrastive approaches to translating Maltese into English for IWSLT 24. The Maltese language shares a large vocabulary with Arabic and Italian languages, thus making it an ideal candidate to test the cross-lingual capabilities of recent state-of-the-art models. We experiment with two end-to-end approaches for our submissions: the Whisper and wav2vec 2.0 models. Our primary system gets a BLEU score of 35.1 on the combined data, whereas our contrastive approach gets 18.5. We also provide a manual analysis of our contrastive approach to identify some pitfalls that may have caused this difference.
Anthology ID:
2024.iwslt-1.33
Volume:
Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)
Month:
August
Year:
2024
Address:
Bangkok, Thailand (in-person and online)
Editors:
Elizabeth Salesky, Marcello Federico, Marine Carpuat
Venue:
IWSLT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
280–285
Language:
URL:
https://aclanthology.org/2024.iwslt-1.33
DOI:
Bibkey:
Cite (ACL):
Kumar Rishu, Aiden Williams, Claudia Borg, and Simon Ostermann. 2024. UoM-DFKI submission to the low resource shared task. In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), pages 280–285, Bangkok, Thailand (in-person and online). Association for Computational Linguistics.
Cite (Informal):
UoM-DFKI submission to the low resource shared task (Rishu et al., IWSLT 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.iwslt-1.33.pdf