Context-Adaptive Document-Level Neural Machine Translation
This work addresses context selection in document-level NMT, offering an incremental improvement over existing methods.
The paper tackled the problem of document-level neural machine translation by proposing a data-adaptive method to select necessary context, resulting in a performance gain of up to 1.99 BLEU points.
Most existing document-level neural machine translation (NMT) models leverage a fixed number of the previous or all global source sentences to handle the context-independent problem in standard NMT. However, the translating of each source sentence benefits from various sizes of context, and inappropriate context may harm the translation performance. In this work, we introduce a data-adaptive method that enables the model to adopt the necessary and useful context. Specifically, we introduce a light predictor into two document-level translation models to select the explicit context. Experiments demonstrate the proposed approach can significantly improve the performance over the previous methods with a gain up to 1.99 BLEU points.