Guided Neural Language Generation for Automated Storytelling
Files
Links to Files
Author/Creator ORCID
Date
Type of Work
Department
Program
Citation of Original Publication
Ammanabrolu, Prithviraj, Ethan Tien, Wesley Cheung, Zhaochen Luo, William Ma, Lara J. Martin, and Mark o. Riedl. "Guided Neural Language Generation for Automated Storytelling" Edited by Francis Ferraro, Ting-Hao ‘Kenneth’ Huang, Stephanie M. Lukin, and Margaret Mitchell. Proceedings of the Second Workshop on Storytelling, August 2019, 46–55. https://doi.org/10.18653/v1/W19-3405.
Rights
Attribution 4.0 International
Subjects
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. Our method outperforms the baseline sequence-to-sequence model. Additionally, we provide results for a full end-to-end automated story generation system, demonstrating how our model works with existing systems designed for the event-to-event problem.