Supervised Visual Attention for Simultaneous Multimodal Machine Translation

TL;DR

This paper introduces the first Transformer-based simultaneous multimodal machine translation model with supervised visual attention, improving translation quality by leveraging image context and phrase-region alignments.

Contribution

The paper presents a novel Transformer-based architecture for simultaneous multimodal translation with supervised visual attention, a first in the field.

Findings

Supervised visual attention improves translation quality.

Fine-tuning with supervision outperforms training from scratch.

Achieves up to 2.3 BLEU and 3.5 METEOR improvements.

Abstract

Recently, there has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality of textual systems. A particular use for such multimodal systems is the task of simultaneous machine translation, where visual context has been shown to complement the partial information provided by the source sentence, especially in the early phases of translation. In this paper, we propose the first Transformer-based simultaneous MMT architecture, which has not been previously explored in the field. Additionally, we extend this model with an auxiliary supervision signal that guides its visual attention mechanism using labelled phrase-region alignments. We perform comprehensive experiments on three language directions and conduct thorough quantitative and qualitative analyses using both automatic metrics and manual inspection. Our results show that (i) supervised visual attention consistently improves the translation quality of the MMT models, and (ii) fine-tuning the MMT with supervision loss enabled leads to better performance than training the MMT from scratch. Compared to the state-of-the-art, our proposed model achieves improvements of up to 2.3 BLEU and 3.5 METEOR points.