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
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7008–7029
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.520
- DOI:
- 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)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-emnlp.520.pdf