Zero-shot fine-grained style transfer: Leveraging distributed continuous style representations to transfer to unseen styles
arXiv preprint arXiv:1911.03914, 2019•arxiv.org
Text style transfer is usually performed using attributes that can take a handful of discrete
values (eg, positive to negative reviews). In this work, we introduce an architecture that can
leverage pre-trained consistent continuous distributed style representations and use them to
transfer to an attribute unseen during training, without requiring any re-tuning of the style
transfer model. We demonstrate the method by training an architecture to transfer text
conveying one sentiment to another sentiment, using a fine-grained set of over 20 sentiment …
values (eg, positive to negative reviews). In this work, we introduce an architecture that can
leverage pre-trained consistent continuous distributed style representations and use them to
transfer to an attribute unseen during training, without requiring any re-tuning of the style
transfer model. We demonstrate the method by training an architecture to transfer text
conveying one sentiment to another sentiment, using a fine-grained set of over 20 sentiment …
Text style transfer is usually performed using attributes that can take a handful of discrete values (e.g., positive to negative reviews). In this work, we introduce an architecture that can leverage pre-trained consistent continuous distributed style representations and use them to transfer to an attribute unseen during training, without requiring any re-tuning of the style transfer model. We demonstrate the method by training an architecture to transfer text conveying one sentiment to another sentiment, using a fine-grained set of over 20 sentiment labels rather than the binary positive/negative often used in style transfer. Our experiments show that this model can then rewrite text to match a target sentiment that was unseen during training.
arxiv.org