A Temporal Variational Model for Story Generation
This addresses the challenge of coherent story generation for natural language processing applications, but it is incremental as it builds on existing methods with mixed success.
The paper tackled the problem of generating stories with better plot development and long-term coherence by using a TD-VAE-based latent vector planning approach for conditioning and reranking. The results showed strong performance in automatic evaluations but disappointing human evaluation for conditioning, with reranking improving over a GPT-2 baseline and matching a hierarchical LSTM model.
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.