Context-Aware Learning for Neural Machine Translation
This addresses the issue of context utilization in document-level translation for machine learning researchers, but it is incremental as it builds on existing transformer-based systems.
The paper tackles the problem of larger-context neural machine translation, where models often ignore helpful context, by proposing a novel learning algorithm with a multilevel pair-wise ranking loss, resulting in a model that is more sensitive to additional context as shown through comparisons with random contexts.
Interest in larger-context neural machine translation, including document-level and multi-modal translation, has been growing. Multiple works have proposed new network architectures or evaluation schemes, but potentially helpful context is still sometimes ignored by larger-context translation models. In this paper, we propose a novel learning algorithm that explicitly encourages a neural translation model to take into account additional context using a multilevel pair-wise ranking loss. We evaluate the proposed learning algorithm with a transformer-based larger-context translation system on document-level translation. By comparing performance using actual and random contexts, we show that a model trained with the proposed algorithm is more sensitive to the additional context.