Visual Cues and Error Correction for Translation Robustness

TL;DR

This paper proposes using visual context and error correction training to enhance neural machine translation robustness against human-like noise, maintaining performance on clean texts.

Contribution

It introduces a multimodal approach with visual cues and a novel error correction training regime to improve translation robustness.

Findings

Visual context improves noise robustness

Error correction training enhances translation stability

Models retain quality on clean texts

Abstract

Neural Machine Translation models are sensitive to noise in the input texts, such as misspelled words and ungrammatical constructions. Existing robustness techniques generally fail when faced with unseen types of noise and their performance degrades on clean texts. In this paper, we focus on three types of realistic noise that are commonly generated by humans and introduce the idea of visual context to improve translation robustness for noisy texts. In addition, we describe a novel error correction training regime that can be used as an auxiliary task to further improve translation robustness. Experiments on English-French and English-German translation show that both multimodal and error correction components improve model robustness to noisy texts, while still retaining translation quality on clean texts.