A Temporal Variational Model for Story Generation

TL;DR

This paper introduces a temporal variational model using TD-VAE for story generation, improving long-term coherence and plot development through latent vector planning and reranking, outperforming some baselines in automatic and human evaluations.

Contribution

It presents a novel latent planning approach with TD-VAE for story generation, demonstrating improved coherence and evaluation performance over baseline models.

Findings

TD-VAE reranking enhances story quality in automatic and human assessments.

Conditioning on latent vectors reduces diversity and narrative progression.

The model outperforms GPT-2 baseline and matches hierarchical LSTM in evaluations.

Abstract

Recent language models can generate interesting and grammatically correct text in story generation but often lack plot development and long-term coherence. This paper experiments with a latent vector planning approach based on a TD-VAE (Temporal Difference Variational Autoencoder), using the model for conditioning and reranking for text generation. The results demonstrate strong performance in automatic cloze and swapping evaluations. The human judgments show stories generated with TD-VAE reranking improve on a GPT-2 medium baseline and show comparable performance to a hierarchical LSTM reranking model. Conditioning on the latent vectors proves disappointing and deteriorates performance in human evaluation because it reduces the diversity of generation, and the models don't learn to progress the narrative. This highlights an important difference between technical task performance (e.g. cloze) and generating interesting stories.