ViTA: Visual-Linguistic Translation by Aligning Object Tags

Kshitij Gupta, Devansh Gautam, Radhika Mamidi


Abstract
Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality datasets to illustrate the contribution of visual modality in the translation systems. In this paper, we propose our system under the team name Volta for the Multimodal Translation Task of WAT 2021 from English to Hindi. We also participate in the textual-only subtask of the same language pair for which we use mBART, a pretrained multilingual sequence-to-sequence model. For multimodal translation, we propose to enhance the textual input by bringing the visual information to a textual domain by extracting object tags from the image. We also explore the robustness of our system by systematically degrading the source text. Finally, we achieve a BLEU score of 44.6 and 51.6 on the test set and challenge set of the multimodal task.
Anthology ID:
2021.wat-1.19
Volume:
Proceedings of the 8th Workshop on Asian Translation (WAT2021)
Month:
August
Year:
2021
Address:
Online
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
166–173
Language:
URL:
https://aclanthology.org/2021.wat-1.19
DOI:
10.18653/v1/2021.wat-1.19
Bibkey:
Cite (ACL):
Kshitij Gupta, Devansh Gautam, and Radhika Mamidi. 2021. ViTA: Visual-Linguistic Translation by Aligning Object Tags. In Proceedings of the 8th Workshop on Asian Translation (WAT2021), pages 166–173, Online. Association for Computational Linguistics.
Cite (Informal):
ViTA: Visual-Linguistic Translation by Aligning Object Tags (Gupta et al., WAT 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2021.wat-1.19.pdf
Code
 kshitij98/vita
Data
Hindi Visual GenomeVisual Genome