Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations
This work addresses a specific bottleneck in machine translation postediting for high-quality outputs, representing an incremental improvement in the field.
The paper tackles the problem of automatic postediting (APE) for high-quality machine translations, where existing systems struggle to decide what to edit. The proposed method, which uses a regularization loss to encourage symmetric self-attention, improves APE quality for high-quality MTs, as demonstrated in experiments.
Automatic postediting (APE) is an automated process to refine a given machine translation (MT). Recent findings present that existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, English-to-German: the better the given MT is, the harder it is to decide what parts to edit and how to fix these errors. One possible solution to this problem is to instill deeper knowledge about the target language into the model. Thus, we propose a linguistically motivated method of regularization that is expected to enhance APE models' understanding of the target language: a loss function that encourages symmetric self-attention on the given MT. Our analysis of experimental results demonstrates that the proposed method helps improving the state-of-the-art architecture's APE quality for high-quality MTs.