Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus

TL;DR

This paper introduces a multi-style transfer model that leverages independently acquired style data and discriminative feedback to control multiple style dimensions simultaneously without requiring joint annotations.

Contribution

It presents a novel approach that relaxes the need for joint style annotations by using independent style data and discriminators, enabling multi-style transfer with preserved content.

Findings

Effective control over multiple style dimensions

Outperforms cascaded uni-dimensional models

Preserves input content during style transfer

Abstract

Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus. A common shortcoming of existing approaches is the prerequisite of joint annotations across all the stylistic dimensions under consideration. Availability of such dataset across a combination of styles limits the extension of these setups to multiple style dimensions. While cascading single-dimensional models across multiple styles is a possibility, it suffers from content loss, especially when the style dimensions are not completely independent of each other. In our work, we relax this requirement of jointly annotated data across multiple styles by using independently acquired data across different style dimensions without any additional annotations. We initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. Through quantitative and qualitative evaluation, we show the ability of our model to control styles across multiple style dimensions while preserving content of the input text. We compare it against baselines involving cascaded state-of-the-art uni-dimensional style transfer models.