OdiaGenAI’s Participation in WMT2024 English-to-Low Resource Multimodal Translation Task

Shantipriya Parida, Shashikanta Sahoo, Sambit Sekhar, Upendra Jena, Sushovan Jena, Kusum Lata


Abstract
This paper covers the system description of the team “ODIAGEN’s” submission to the WMT~2024 English-to-Low-Resource Multimodal Translation Task. We participated in the English-to-Low Resource Multimodal Translation Task, in two of the tasks, i.e. Text-only Translation and Multi-modal Translation. For Text-only Translation, we trained the Mistral-7B model for English to Multi-lingual (Hindi, Bengali, Malayalam, Hausa). For Multi-modal Translation (using both image and text), we trained the PaliGemma-3B model for English to Hindi translation.
Anthology ID:
2024.wmt-1.77
Volume:
Proceedings of the Ninth Conference on Machine Translation
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
823–828
Language:
URL:
https://aclanthology.org/2024.wmt-1.77
DOI:
Bibkey:
Cite (ACL):
Shantipriya Parida, Shashikanta Sahoo, Sambit Sekhar, Upendra Jena, Sushovan Jena, and Kusum Lata. 2024. OdiaGenAI’s Participation in WMT2024 English-to-Low Resource Multimodal Translation Task. In Proceedings of the Ninth Conference on Machine Translation, pages 823–828, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
OdiaGenAI’s Participation in WMT2024 English-to-Low Resource Multimodal Translation Task (Parida et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.77.pdf