Context in Neural Machine Translation: A Review of Models and Evaluations

TL;DR

This review examines recent advances in neural machine translation, focusing on how context has been modeled and evaluated to address translation limitations, highlighting methods that leverage contextual information for improved accuracy.

Contribution

It provides a comprehensive overview of recent models and evaluation methods for incorporating context in NMT, distinguishing approaches targeting specific phenomena from those using broader context.

Findings

Analysis of limitations in current contextual NMT models

Evaluation of methods addressing contextual phenomena

Identification of approaches leveraging unstructured context

Abstract

This review paper discusses how context has been used in neural machine translation (NMT) in the past two years (2017-2018). Starting with a brief retrospect on the rapid evolution of NMT models, the paper then reviews studies that evaluate NMT output from various perspectives, with emphasis on those analyzing limitations of the translation of contextual phenomena. In a subsequent version, the paper will then present the main methods that were proposed to leverage context for improving translation quality, and distinguishes methods that aim to improve the translation of specific phenomena from those that consider a wider unstructured context.