Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation

TL;DR

This paper introduces a flexible unsupervised method for text attribute transfer that edits entangled latent representations using a gradient-based algorithm, enabling controlled and multi-aspect transfer without parallel data.

Contribution

It proposes a Transformer-based autoencoder with a novel gradient-based editing algorithm for flexible, multi-aspect, and controllable unsupervised text attribute transfer.

Findings

Achieves competitive performance on three datasets.

Enables control over transfer degree.

Supports multi-aspect attribute transfer.

Abstract

Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e.g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content. The dominant approaches are trying to model the content-independent attribute separately, e.g., learning different attributes' representations or using multiple attribute-specific decoders. However, it may lead to inflexibility from the perspective of controlling the degree of transfer or transferring over multiple aspects at the same time. To address the above problems, we propose a more flexible unsupervised text attribute transfer framework which replaces the process of modeling attribute with minimal editing of latent representations based on an attribute classifier. Specifically, we first propose a Transformer-based autoencoder to learn an entangled latent representation for a discrete text, then we transform the attribute transfer task to an optimization problem and propose the Fast-Gradient-Iterative-Modification algorithm to edit the latent representation until conforming to the target attribute. Extensive experimental results demonstrate that our model achieves very competitive performance on three public data sets. Furthermore, we also show that our model can not only control the degree of transfer freely but also allow to transfer over multiple aspects at the same time.