The Candide model: How narratives emerge where observations meet beliefs

Research output: Chapter in Book/Report/Conference proceedingConference paper

8 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationProceedings of the The 5th Workshop on Narrative Understanding
PublisherAssociation for Computational Linguistics
Number of pages10
Publication statusPublished - Jul 2023
Event5th Workshop on Narrative Understanding - Toronto, Canada
Duration: 14 Jul 202314 Jul 2023


Workshop5th Workshop on Narrative Understanding
Abbreviated titleWNU
Internet address


  • Fluid Construction Grammar
  • Construction Grammar
  • Computational Construction Grammar


Dive into the research topics of 'The Candide model: How narratives emerge where observations meet beliefs'. Together they form a unique fingerprint.

Cite this