Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes

Zhiyu Lin, Mark Riedl


Abstract
We describe a Plug-and-Play controllable language generation framework, Plug-and-Blend, that allows a human user to input multiple control codes (topics). In the context of automated story generation, this allows a human user lose or fine grained control of the topics that will appear in the generated story, and can even allow for overlapping, blended topics. We show that our framework, working with different generation models, controls the generation towards given continuous-weighted control codes while keeping the generated sentences fluent, demonstrating strong blending capability.
Anthology ID:
2021.nuse-1.7
Volume:
Proceedings of the Third Workshop on Narrative Understanding
Month:
June
Year:
2021
Address:
Virtual
Editors:
Nader Akoury, Faeze Brahman, Snigdha Chaturvedi, Elizabeth Clark, Mohit Iyyer, Lara J. Martin
Venues:
NUSE | WNU
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
62–71
Language:
URL:
https://aclanthology.org/2021.nuse-1.7
DOI:
10.18653/v1/2021.nuse-1.7
Bibkey:
Cite (ACL):
Zhiyu Lin and Mark Riedl. 2021. Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes. In Proceedings of the Third Workshop on Narrative Understanding, pages 62–71, Virtual. Association for Computational Linguistics.
Cite (Informal):
Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes (Lin & Riedl, NUSE-WNU 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nuse-1.7.pdf
Code
 xxbidiao/plug-and-blend