The Candide model: How narratives emerge where observations meet beliefs

Paul Van Eecke; Lara Verheyen; Tom Willaert; Katrien Beuls

doi:10.18653/v1/2023.wnu-1.7

The Candide model: How narratives emerge where observations meet beliefs

Paul Van Eecke, Lara Verheyen, Tom Willaert, Katrien Beuls

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Research

1 Citation (Scopus)

38 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings of the The 5th Workshop on Narrative Understanding
Editors	Nader Akoury, Elizabeth Clark, Mohit Iyyer, Snigdha Chaturvedi, Faeze Brahman, Khyathi Raghavi Chandu
Publisher	Association for Computational Linguistics
Pages	48-57
Number of pages <span style="color:red"p> <font size="1.5"> ✽ </span> </font>	10
ISBN (Electronic)	9781959429920
DOIs	https://doi.org/10.18653/v1/2023.wnu-1.7
Publication status	Published - Jul 2023
Event	5th Workshop on Narrative Understanding - Toronto, Canada Duration: 14 Jul 2023 → 14 Jul 2023 https://sites.google.com/umass.edu/wnu2023

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Workshop

Workshop	5th Workshop on Narrative Understanding
Abbreviated title	WNU
Country/Territory	Canada
City	Toronto
Period	14/07/23 → 14/07/23
Internet address	https://sites.google.com/umass.edu/wnu2023

Bibliographical note

Funding Information:
The research reported on in this paper received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreements no. 951846 (MUHAI - Meaning and Understanding in Human-centric AI) and no. 101094752 (SoMe4Dem - Social Media for Democracy – understanding the causal mechanisms of digital citizenship), from the Research Foundation Flanders (FWO) through a postdoctoral grant awarded to Paul Van Eecke (grant no. 75929) and from the Flemish Government under the ‘Flanders AI Research Program’.

Publisher Copyright:
© 2023 Association for Computational Linguistics.

Keywords

Fluid Construction Grammar
Construction Grammar
Computational Construction Grammar

Access to Document

10.18653/v1/2023.wnu-1.7

2023.wnu-1.7Final published version, 248 KBLicence: CC BY

https://aclanthology.org/2023.wnu-1.7.pdfLicence: CC BY

Cite this

Van Eecke, P., Verheyen, L., Willaert, T., & Beuls, K. (2023). The Candide model: How narratives emerge where observations meet beliefs. In N. Akoury, E. Clark, M. Iyyer, S. Chaturvedi, F. Brahman, & K. R. Chandu (Eds.), Proceedings of the The 5th Workshop on Narrative Understanding (pp. 48-57). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.wnu-1.7

Van Eecke, Paul ; Verheyen, Lara ; Willaert, Tom ; Beuls, Katrien. / The Candide model: How narratives emerge where observations meet beliefs. Proceedings of the The 5th Workshop on Narrative Understanding. editor / Nader Akoury ; Elizabeth Clark ; Mohit Iyyer ; Snigdha Chaturvedi ; Faeze Brahman ; Khyathi Raghavi Chandu. Association for Computational Linguistics, 2023. pp. 48-57 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{b0d5007ff86f44289451c5b11f8be912,

title = "The Candide model: How narratives emerge where observations meet beliefs",

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.",

keywords = "Fluid Construction Grammar, Construction Grammar, Computational Construction Grammar",

author = "{Van Eecke}, Paul and Lara Verheyen and Tom Willaert and Katrien Beuls",

note = "Funding Information: The research reported on in this paper received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under grant agreements no. 951846 (MUHAI - Meaning and Understanding in Human-centric AI) and no. 101094752 (SoMe4Dem - Social Media for Democracy – understanding the causal mechanisms of digital citizenship), from the Research Foundation Flanders (FWO) through a postdoctoral grant awarded to Paul Van Eecke (grant no. 75929) and from the Flemish Government under the {\textquoteleft}Flanders AI Research Program{\textquoteright}. Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 5th Workshop on Narrative Understanding, WNU ; Conference date: 14-07-2023 Through 14-07-2023",

year = "2023",

month = jul,

doi = "10.18653/v1/2023.wnu-1.7",

language = "English",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

pages = "48--57",

editor = "Nader Akoury and Elizabeth Clark and Mohit Iyyer and Snigdha Chaturvedi and Faeze Brahman and Chandu, {Khyathi Raghavi}",

booktitle = "Proceedings of the The 5th Workshop on Narrative Understanding",

url = "https://sites.google.com/umass.edu/wnu2023",

}

Van Eecke, P , Verheyen, L , Willaert, T & Beuls, K 2023, The Candide model: How narratives emerge where observations meet beliefs. in N Akoury, E Clark, M Iyyer, S Chaturvedi, F Brahman & KR Chandu (eds), Proceedings of the The 5th Workshop on Narrative Understanding. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 48-57, 5th Workshop on Narrative Understanding, Toronto, Canada, 14/07/23. https://doi.org/10.18653/v1/2023.wnu-1.7

The Candide model: How narratives emerge where observations meet beliefs. / Van Eecke, Paul ; Verheyen, Lara ; Willaert, Tom; Beuls, Katrien.

Proceedings of the The 5th Workshop on Narrative Understanding. ed. / Nader Akoury; Elizabeth Clark; Mohit Iyyer; Snigdha Chaturvedi; Faeze Brahman; Khyathi Raghavi Chandu. Association for Computational Linguistics, 2023. p. 48-57 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Research

TY - GEN

T1 - The Candide model: How narratives emerge where observations meet beliefs

AU - Van Eecke, Paul

AU - Verheyen, Lara

AU - Willaert, Tom

AU - Beuls, Katrien

N1 - Funding Information: The research reported on in this paper received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreements no. 951846 (MUHAI - Meaning and Understanding in Human-centric AI) and no. 101094752 (SoMe4Dem - Social Media for Democracy – understanding the causal mechanisms of digital citizenship), from the Research Foundation Flanders (FWO) through a postdoctoral grant awarded to Paul Van Eecke (grant no. 75929) and from the Flemish Government under the ‘Flanders AI Research Program’. Publisher Copyright: © 2023 Association for Computational Linguistics.

PY - 2023/7

Y1 - 2023/7

N2 - 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.

AB - 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.

KW - Fluid Construction Grammar

KW - Construction Grammar

KW - Computational Construction Grammar

UR - http://www.scopus.com/inward/record.url?scp=85175657027&partnerID=8YFLogxK

U2 - 10.18653/v1/2023.wnu-1.7

DO - 10.18653/v1/2023.wnu-1.7

M3 - Conference paper

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 48

EP - 57

BT - Proceedings of the The 5th Workshop on Narrative Understanding

A2 - Akoury, Nader

A2 - Clark, Elizabeth

A2 - Iyyer, Mohit

A2 - Chaturvedi, Snigdha

A2 - Brahman, Faeze

A2 - Chandu, Khyathi Raghavi

PB - Association for Computational Linguistics

T2 - 5th Workshop on Narrative Understanding

Y2 - 14 July 2023 through 14 July 2023

ER -

Van Eecke P , Verheyen L , Willaert T, Beuls K. The Candide model: How narratives emerge where observations meet beliefs. In Akoury N, Clark E, Iyyer M, Chaturvedi S, Brahman F, Chandu KR, editors, Proceedings of the The 5th Workshop on Narrative Understanding. Association for Computational Linguistics. 2023. p. 48-57. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). https://doi.org/10.18653/v1/2023.wnu-1.7

The Candide model: How narratives emerge where observations meet beliefs

Abstract

Publication series

Workshop

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

VLAAI1: Flanders Artificial Intelligence Research program (FAIR) – second cycle

EUAR117: SoMe4Dem : Social media for democracy – understanding the causal mechanisms of digital citizenship

OZR4048: Towards a mechanistic understanding of the emergence, evolution, acquisition and processing of human-like languages in populations of autonomous agents

Cite this

The Candide model: How narratives emerge where observations meet beliefs

Abstract

Publication series

Workshop

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Projects

VLAAI1: Flanders Artificial Intelligence Research program (FAIR) – second cycle

EUAR117: SoMe4Dem : Social media for democracy – understanding the causal mechanisms of digital citizenship

OZR4048: Towards a mechanistic understanding of the emergence, evolution, acquisition and processing of human-like languages in populations of autonomous agents

Cite this