Context in Neural Machine Translation: A Review of Models and Evaluations
It provides a synthesis of recent research on context in NMT, which is incremental as it reviews existing studies without introducing new findings.
This review paper examines how context has been utilized in neural machine translation (NMT) from 2017 to 2018, focusing on evaluating NMT output to identify limitations in translating contextual phenomena and outlining methods to leverage context for improving translation quality.
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.