Soft Contextual Data Augmentation for Neural Machine Translation
Meeting of the Association for Computational Linguistics, 2019.
We have presented soft contextual data augmentation for neural machine translation, which replaces a randomly chosen word with a soft distributional representation
While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap...More
PPT (Upload PPT)