Abstract
Automated storytelling has long captured the attention of researchers for the ubiquity of narratives in everyday life. The best human-crafted stories exhibit coherent plot, strong characters, and adherence to genres, attributes that current states-of-the-art still struggle to produce, even using transformer architectures. In this paper, we analyze works in story generation that utilize machine learning approaches to (1) address story generation controllability, (2) incorporate commonsense knowledge, (3) infer reasonable character actions, and (4) generate creative language.- Anthology ID:
- 2021.nuse-1.8
- Volume:
- Proceedings of the Third Workshop on Narrative Understanding
- Month:
- June
- Year:
- 2021
- Address:
- Virtual
- Venue:
- NUSE
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 72–83
- Language:
- URL:
- https://aclanthology.org/2021.nuse-1.8
- DOI:
- 10.18653/v1/2021.nuse-1.8
- Cite (ACL):
- Amal Alabdulkarim, Siyan Li, and Xiangyu Peng. 2021. Automatic Story Generation: Challenges and Attempts. In Proceedings of the Third Workshop on Narrative Understanding, pages 72–83, Virtual. Association for Computational Linguistics.
- Cite (Informal):
- Automatic Story Generation: Challenges and Attempts (Alabdulkarim et al., NUSE 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.nuse-1.8.pdf
- Data
- ATOMIC, CommonsenseQA, ConceptNet, GLUCOSE, WritingPrompts