TVStoryGen: A Dataset for Generating Stories with Character Descriptions
This provides a domain-specific dataset for story generation with character constraints, though it's incremental relative to existing story generation datasets.
The authors introduced TVStoryGen, a dataset of 26k professionally-written TV episode recaps averaging 1,868.7 tokens, requiring generation from brief summaries and character documents. They found a hierarchical model with oracle content selectors performed best on automatic metrics, though qualitative analysis revealed faithfulness issues.
We introduce TVStoryGen, a story generation dataset that requires generating detailed TV show episode recaps from a brief summary and a set of documents describing the characters involved. Unlike other story generation datasets, TVStoryGen contains stories that are authored by professional screen-writers and that feature complex interactions among multiple characters. Generating stories in TVStoryGen requires drawing relevant information from the lengthy provided documents about characters based on the brief summary. In addition, we propose to train reverse models on our dataset for evaluating the faithfulness of generated stories. We create TVStoryGen from fan-contributed websites, which allows us to collect 26k episode recaps with 1868.7 tokens on average. Empirically, we take a hierarchical story generation approach and find that the neural model that uses oracle content selectors for character descriptions demonstrates the best performance on automatic metrics, showing the potential of our dataset to inspire future research on story generation with constraints. Qualitative analysis shows that the best-performing model sometimes generates content that is unfaithful to the short summaries, suggesting promising directions for future work.