TVRecap: A Dataset for Generating Stories with Character Descriptions

Abstract

We introduce TVRECAP, 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, TVRECAP contains stories that are authored by professional screenwriters and that feature complex interactions among multiple characters. Generating stories in TVRECAP requires drawing relevant information from the lengthy provided documents about characters based on the brief summary. In addition, by swapping the input and output, TVRECAP can serve as a challenging testbed for abstractive summarization. We create TVRECAP from fancontributed 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. 1

SNaC: Coherence Error Detection for Narrative Summarization

“…Recent work has introduced a number of narrative summarization tasks, for books (Ladhak et al, 2020;, screenplays Papalampidi et al, 2020;Chen and Gimpel, 2021), and dialogue (Zhong et al, 2021). In our work, we study coherence errors in two domains, books and movie screenplays, although our taxonomy and annotation methodology are broadly applicable.…”