Simultaneous Machine Translation with Visual Context

TL;DR

This paper investigates how incorporating visual context, especially object region features, can enhance simultaneous machine translation by improving translation quality and handling linguistic differences.

Contribution

It demonstrates that visual information, particularly explicit object region features, significantly improves SiMT performance and translation accuracy in low latency scenarios.

Findings

Visual context improves translation quality by up to 3 BLEU points.

Explicit object region features outperform global features in multimodal SiMT.

Multimodal models better handle gender and word order differences.

Abstract

Simultaneous machine translation (SiMT) aims to translate a continuous input text stream into another language with the lowest latency and highest quality possible. The translation thus has to start with an incomplete source text, which is read progressively, creating the need for anticipation. In this paper, we seek to understand whether the addition of visual information can compensate for the missing source context. To this end, we analyse the impact of different multimodal approaches and visual features on state-of-the-art SiMT frameworks. Our results show that visual context is helpful and that visually-grounded models based on explicit object region information are much better than commonly used global features, reaching up to 3 BLEU points improvement under low latency scenarios. Our qualitative analysis illustrates cases where only the multimodal systems are able to translate correctly from English into gender-marked languages, as well as deal with differences in word order, such as adjective-noun placement between English and French.