Unsupervised style transfer aims to change the style of an input sentence while preserving its original content without using parallel training data . In current dominant approaches, owing to the lack of fine-grained control on the influence from the target style, they are unable to yield desirable output sentences… In this paper, we propose a novel attentional sequence-to-sequence (Seq2seq) model that dynamically exploits the relevance of each output word to the . target style . We fine-tune this model using a carefully-designed objective function involving style transfer, style relevance consistency, content preservation and fluency modeling loss terms . Experimental results show that our proposed model achieves state-of-the-art performance in terms of both transfer accuracy and content preservation . The . proposed model achieved state- of the . model achieves . the . proposed models achieves state of the art performance in . the proposed model achieve state-for-the.-art performance and . the model achieves the . transfer accuracy in terms of both transfers accuracy and . content preservation

Links: PDF - Abstract

Code :


Keywords : style - model - transfer - proposed - achieves -

Leave a Reply

Your email address will not be published.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


Enjoy this blog? Please spread the word :)