Story Realization: Expanding Plot Events into Sentences

Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and ( 2 ) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events. We provide results-including a human subjects study-for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches 1 . Introduction Automated story plot generation is the problem of creating a sequence of main plot points for a story in a given domain. Generated plots must remain consistent across the entire story, preserve long-term dependencies, and make use of commonsense and schematic knowledge (Wiseman, Shieber, and Rush 2017). Early work focused on symbolic planning and case-based reasoning (