DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting
This addresses the task of author stylized rewriting for applications like content generation, but it is incremental as it builds on prior Transformer-based methods.
The paper tackled the problem of rewriting text in a specific author's style without parallel data, proposing a Director-Generator framework that improves meaning retention and fluency, with experiments showing significant improvements over existing methods on small corpora.
Author stylized rewriting is the task of rewriting an input text in a particular author's style. Recent works in this area have leveraged Transformer-based language models in a denoising autoencoder setup to generate author stylized text without relying on a parallel corpus of data. However, these approaches are limited by the lack of explicit control of target attributes and being entirely data-driven. In this paper, we propose a Director-Generator framework to rewrite content in the target author's style, specifically focusing on certain target attributes. We show that our proposed framework works well even with a limited-sized target author corpus. Our experiments on corpora consisting of relatively small-sized text authored by three distinct authors show significant improvements upon existing works to rewrite input texts in target author's style. Our quantitative and qualitative analyses further show that our model has better meaning retention and results in more fluent generations.