Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations

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...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jung, Baikjin, Lee, Myungji, Lee, Jong-Hyeok, Kim, Yunsu
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 17.06.2023
Subjects
Machine translation
Regularization
Symmetry
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422