Abstract
This paper presents the Candide model as a computational architecture for modelling human-like, narrative-based language understanding. The model starts from the idea that narratives emerge through the process of interpreting novel linguistic observations, such as utterances, paragraphs and texts, with respect to previously acquired knowledge and beliefs. Narratives are personal, as they are rooted in past experiences, and constitute perspectives on the world that might motivate different interpretations of the same observations. Concretely, the Candide model operationalises this idea by dynamically modelling the belief systems and background knowledge of individual agents, updating these as new linguistic observations come in, and exposing them to a logic reasoning engine that reveals the possible sources of divergent interpretations. Apart from introducing the foundational ideas, we also present a proof-of-concept implementation that demonstrates the approach through a number of illustrative examples.- Anthology ID:
- 2023.wnu-1.7
- Volume:
- Proceedings of the The 5th Workshop on Narrative Understanding
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Venue:
- WNU
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 48–57
- Language:
- URL:
- https://aclanthology.org/2023.wnu-1.7
- DOI:
- Cite (ACL):
- Paul Van Eecke, Lara Verheyen, Tom Willaert, and Katrien Beuls. 2023. The Candide model: How narratives emerge where observations meet beliefs. In Proceedings of the The 5th Workshop on Narrative Understanding, pages 48–57, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- The Candide model: How narratives emerge where observations meet beliefs (Van Eecke et al., WNU 2023)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2023.wnu-1.7.pdf