PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking

Hannah Rashkin, Asli Celikyilmaz, Yejin Choi, Jianfeng Gao


Abstract
We propose the task of outline-conditioned story generation: given an outline as a set of phrases that describe key characters and events to appear in a story, the task is to generate a coherent narrative that is consistent with the provided outline. This task is challenging as the input only provides a rough sketch of the plot, and thus, models need to generate a story by interweaving the key points provided in the outline. This requires the model to keep track of the dynamic states of the latent plot, conditioning on the input outline while generating the full story. We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative. Comprehensive experiments over three fiction and non-fiction datasets demonstrate that large-scale language models, such as GPT-2 and Grover, despite their impressive generation performance, are not sufficient in generating coherent narratives for the given outline, and dynamic plot state tracking is important for composing narratives with tighter, more consistent plots.
Anthology ID:
2020.emnlp-main.349
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4274–4295
Language:
URL:
https://aclanthology.org/2020.emnlp-main.349
DOI:
10.18653/v1/2020.emnlp-main.349
Bibkey:
Cite (ACL):
Hannah Rashkin, Asli Celikyilmaz, Yejin Choi, and Jianfeng Gao. 2020. PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4274–4295, Online. Association for Computational Linguistics.
Cite (Informal):
PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking (Rashkin et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.349.pdf
Video:
 https://slideslive.com/38938968
Code
 hrashkin/plotmachines +  additional community code
Data
WritingPrompts