English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa

Ali Hatami, Shubhanker Banerjee, Mihael Arcan, Bharathi Chakravarthi, Paul Buitelaar, John Mccrae


Abstract
Multimodal machine translation leverages multiple data modalities to enhance translation quality, particularly for low-resourced languages. This paper uses a Multimodal model that integrates visual information with textual data to improve translation accuracy from English to Hindi, Malayalam, Bengali, and Hausa. This approach employs a gated fusion mechanism to effectively combine the outputs of textual and visual encoders, enabling more nuanced translations that consider both language and contextual visual cues. The performance of the multimodal model was evaluated against the text-only machine translation model based on BLEU, ChrF2 and TER. Experimental results demonstrate that the multimodal approach consistently outperforms the text-only baseline, highlighting the potential of integrating visual information in low-resourced language translation tasks.
Anthology ID:
2024.wmt-1.76
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:
815–822
Language:
URL:
https://aclanthology.org/2024.wmt-1.76
DOI:
Bibkey:
Cite (ACL):
Ali Hatami, Shubhanker Banerjee, Mihael Arcan, Bharathi Chakravarthi, Paul Buitelaar, and John Mccrae. 2024. English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa. In Proceedings of the Ninth Conference on Machine Translation, pages 815–822, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
English-to-Low-Resource Translation: A Multimodal Approach for Hindi, Malayalam, Bengali, and Hausa (Hatami et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.76.pdf