DGST: a Dual-Generator Network for Text Style Transfer
This work addresses text style transfer for NLP applications, but it is incremental as it builds on existing methods with a simpler architecture.
The authors tackled text style transfer by proposing DGST, a dual-generator network that does not require discriminators or parallel data, achieving competitive performance on Yelp and IMDb datasets compared to more complex baselines.
We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.