Story Realization: Expanding Plot Events into Sentences

Abstract

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.

In proceedings of AAAI 2020

References in corpus (12)

• Sequence to Sequence Learning with Neural Networks
• Narrative Planning: Balancing Plot and Character
• Regularizing and Optimizing LSTM Language Models
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Event Representations for Automated Story Generation with Deep Neural Nets
• Hierarchical Neural Story Generation
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• Controllable Neural Story Plot Generation via Reward Shaping
• Story Generation from Sequence of Independent Short Descriptions
• Challenges in Data-to-Document Generation
• Plan-And-Write: Towards Better Automatic Storytelling
• Toward Automated Quest Generation in Text-Adventure Games

Cited by in corpus (3)

• Learning Norms from Stories: A Prior for Value Aligned Agents
• DYPLODOC: Dynamic Plots for Document Classification
• GraphPlan: Story Generation by Planning with Event Graph