Transformer-based Conditional Variational Autoencoder for Controllable Story Generation

TL;DR

This paper proposes a Transformer-based CVAE model that combines latent variable modeling with pre-trained language models to improve controllability in open-domain story generation while maintaining high effectiveness.

Contribution

It introduces a novel integration of latent variables with Transformer architectures, specifically GPT-2, to enhance controllability in neural story generation.

Findings

Achieves state-of-the-art conditional story generation.

Demonstrates strong representation learning capabilities.

Provides improved controllability in generated stories.

Abstract

We investigate large-scale latent variable models (LVMs) for neural story generation -- an under-explored application for open-domain long text -- with objectives in two threads: generation effectiveness and controllability. LVMs, especially the variational autoencoder (VAE), have achieved both effective and controllable generation through exploiting flexible distributional latent representations. Recently, Transformers and its variants have achieved remarkable effectiveness without explicit latent representation learning, thus lack satisfying controllability in generation. In this paper, we advocate to revive latent variable modeling, essentially the power of representation learning, in the era of Transformers to enhance controllability without hurting state-of-the-art generation effectiveness. Specifically, we integrate latent representation vectors with a Transformer-based pre-trained architecture to build conditional variational autoencoder (CVAE). Model components such as encoder, decoder and the variational posterior are all built on top of pre-trained language models -- GPT2 specifically in this paper. Experiments demonstrate state-of-the-art conditional generation ability of our model, as well as its excellent representation learning capability and controllability.