Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation
This work addresses the need for more coherent and consistent translations in document-level machine translation, representing an incremental improvement over existing hierarchical attention methods.
The paper tackled the problem of context modeling in document-level neural machine translation by proposing a query-guided capsule network to cluster context information into different perspectives, resulting in significantly outperforming strong baselines on multiple datasets across different domains.
Context modeling is essential to generate coherent and consistent translation for Document-level Neural Machine Translations. The widely used method for document-level translation usually compresses the context information into a representation via hierarchical attention networks. However, this method neither considers the relationship between context words nor distinguishes the roles of context words. To address this problem, we propose a query-guided capsule networks to cluster context information into different perspectives from which the target translation may concern. Experiment results show that our method can significantly outperform strong baselines on multiple data sets of different domains.