The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data . In this paper, we study how to augment parallel data and propose novel and simple data augmentation methods . Experiments demonstrate that our augmented parallel data largely helps improve formality style transfer when it is used to pre-train the model, leading to the state-of-the-art results in the GYAFC benchmark dataset .

Links: PDF - Abstract

Code :

None

Keywords : data - style - formality - transfer - parallel -

Leave a Reply

Your email address will not be published. Required fields are marked *