Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles
This work addresses the limitation of discrete style attributes in text style transfer, offering a method for fine-grained and zero-shot applications, though it is incremental in extending existing techniques to new domains.
The paper tackles the problem of text style transfer for unseen styles by introducing an architecture that leverages pre-trained continuous distributed style representations, enabling transfer to over 20 fine-grained sentiment labels without re-tuning, and demonstrates this capability on unseen sentiments.
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.