Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning

Xiangyu Peng, Siyan Li, Sarah Wiegreffe, Mark Riedl


Abstract
Transformer-based language model approaches to automated story generation currently provide state-of-the-art results. However, they still suffer from plot incoherence when generatingnarratives over time, and critically lack basiccommonsense reasoning. Furthermore, existing methods generally focus only on single-character stories, or fail to track charactersat all. To improve the coherence of generated narratives and to expand the scope ofcharacter-centric narrative generation, we introduce Commonsense-inference Augmentedneural StoryTelling (CAST), a framework forintroducing commonsense reasoning into thegeneration process with the option to model theinteraction between multiple characters. Wefind that our CAST method produces significantly more coherent, on-topic, enjoyable andfluent stories than existing models in both thesingle-character and two-character settings inthree storytelling domains.
Anthology ID:
2022.findings-emnlp.520
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7008–7029
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.520
DOI:
10.18653/v1/2022.findings-emnlp.520
Bibkey:
Cite (ACL):
Xiangyu Peng, Siyan Li, Sarah Wiegreffe, and Mark Riedl. 2022. Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 7008–7029, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning (Peng et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.520.pdf
Video:
 https://aclanthology.org/2022.findings-emnlp.520.mp4