Publication
UoM-DFKI submission to the low resource shared task
Rishu Kumar; Aiden Williams; Claudia Borg; Simon Ostermann
In: Elizabeth Salesky; Marcello Federico; Marine Carpuat (Hrsg.). Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024). International Conference on Spoken Language Translation (IWSLT-2024), August 15-16, Bangkok, Thailand, Pages 280-285, Association for Computational Linguistics, 2024.
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.