This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to the lack of diversity of the generated texts. FVN addresses these issues by learning disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity, while at the same time generating fluent text. We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.
@article{arxiv.2009.12046,
title = {Controllable Text Generation with Focused Variation},
author = {Lei Shu and Alexandros Papangelis and Yi-Chia Wang and Gokhan Tur and Hu Xu and Zhaleh Feizollahi and Bing Liu and Piero Molino},
journal= {arXiv preprint arXiv:2009.12046},
year = {2020}
}