Decomposing Textual Information For Style Transfer
Ivan P. Yamshchikov | Viacheslav Shibaev | Aleksander Nagaev | Jürgen Jost | Alexey Tikhonov
Proceedings of the 3rd Workshop on Neural Generation and Translation
This paper focuses on latent representations that could effectively decompose different aspects of textual information. Using a framework of style transfer for texts, we propose several empirical methods to assess information decomposition quality. We validate these methods with several state-of-the-art textual style transfer methods. Higher quality of information decomposition corresponds to higher performance in terms of bilingual evaluation understudy (BLEU) between output and human-written reformulations.