ViTA: Visual-Linguistic Translation by Aligning Object Tags

TL;DR

This paper introduces ViTA, a multimodal translation system that enhances textual input with visual object tags to improve English-Hindi translation, demonstrating competitive BLEU scores and robustness to source text degradation.

Contribution

The paper proposes a novel approach to incorporate visual information into translation by translating object tags into text, advancing multimodal translation techniques.

Findings

Achieved BLEU scores of 44.6 and 51.6 on test and challenge sets.

Enhanced translation robustness through systematic source text degradation.

Demonstrated effectiveness of visual object tags in multimodal translation.

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.