Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
Abstract
Conditional Text Generation has drawn much attention as a topic of Natural Language Generation (NLG) which provides the possibility for humans to control the properties of generated contents. Current conditional generation models cannot handle emerging conditions due to their joint end-to-end learning fashion. When a new condition added, these techniques require full retraining. In this paper, we present a new framework named Pre-train and Plug-in Variational Auto-Encoder (PPVAE) towards flexible conditional text generation. PPVAE decouples the text generation module from the condition representation module to allow "one-to-many" conditional generation. When a fresh condition emerges, only a lightweight network needs to be trained and works as a plug-in for PPVAE, which is efficient and desirable for real-world applications. Extensive experiments demonstrate the superiority of PPVAE against the existing alternatives with better conditionality and diversity but less training effort.
Cite
@article{arxiv.1911.03882,
title = {Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders},
author = {Yu Duan and Canwen Xu and Jiaxin Pei and Jialong Han and Chenliang Li},
journal= {arXiv preprint arXiv:1911.03882},
year = {2020}
}
Comments
Accepted as a long paper at ACL 2020