Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles

Abstract

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.

References in corpus (8)

• CTRL: A Conditional Transformer Language Model for Controllable Generation
• Phrase-Based & Neural Unsupervised Machine Translation
• Unsupervised Machine Translation Using Monolingual Corpora Only
• Style Transfer as Unsupervised Machine Translation
• Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation
• Style Transfer in Text: Exploration and Evaluation
• Structuring Latent Spaces for Stylized Response Generation
• Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning

Cited by in corpus (5)

• Recipes for Safety in Open-domain Chatbots
• Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions
• Controlling Style in Generated Dialogue
• From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey
• Learning to Generate Multiple Style Transfer Outputs for an Input Sentence