Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/148533| Title: | UoM-DFKI submission to the low resource shared task |
| Authors: | Rishu, Kumar Williams, Aiden Borg, Claudia Ostermann, Simon |
| Keywords: | Computational linguistics Automatic speech recognition Speech processing systems Machine translating Translating and interpreting |
| Issue Date: | 2024 |
| Publisher: | Association for Computational Linguistics |
| Citation: | Rishu, K., Williams, A., Borg, C. & Ostermann, S. (2024). UoM-DFKI submission to the low resource shared task. 21st International Conference on Spoken Language Translation (IWSLT 2024), Bangkok. 280-285. |
| 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. |
| URI: | https://www.um.edu.mt/library/oar/handle/123456789/148533 |
| Appears in Collections: | Scholarly Works - FacICTAI |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2024.iwslt-1.33.pdf | 129.86 kB | Adobe PDF | View/Open |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.