The computational learning of construction grammars: State of the art and prospective roadmap

Jonas Doumen; Veronica Juliana Schmalz; Katrien Beuls; Paul Van Eecke

doi:10.1075/cf.23026.dou

The computational learning of construction grammars: State of the art and prospective roadmap

Jonas Doumen, Veronica Juliana Schmalz, Katrien Beuls, Paul Van Eecke

Research output: Contribution to journal › Article › peer-review

14 Downloads (Pure)

Abstract

This paper documents and reviews the state of the art concerning computational models of construction grammar learning. It brings together prior work on the computational learning of form-meaning pairings, which has so far been studied in several distinct areas of research. The goal of this paper is threefold. First of all, it aims to synthesise the variety of methodologies that have been proposed to date and the results that have been obtained. Second, it aims to identify those parts of the challenge that have been successfully tackled and reveal those that require further research. Finally, it aims to provide a roadmap which can help to boost and streamline future research efforts on the computational learning of large-scale, usage-based construction grammars.

Original language	English
Number of pages	34
Journal	Constructions and Frames
Volume	17
Issue number	1
DOIs	https://doi.org/10.1075/cf.23026.dou
Publication status	Published - 2025

Bibliographical note

Funding Information:
The research reported in this paper was funded by the European Union\u2019s Horizon 2020 research and innovation programme under grant agreement No. 951846, the Flemish Government under the Onderzoeksprogramma Artifici\u00EBle Intelligentie (AI) Vlaanderen programme, the Walloon AI Flagship programme ARIAC, and the F.R.S.-FNRS - FWO WEAVE project HERMES I under grant numbers T002724F (F.R.S.-FNRS) and G0AGU24N (FWO). PVE was supported by a postdoctoral fellowship of the Research Foundation Flanders (FWO) with grant No. 75929. JD was funded by the imec.icon project COSMO (HBC.2018.0531) and the imec Smart Education covenant funding Edulab. VJS was funded through a doctoral fellowship awarded by the Research Foundation Flanders (FWO) with grant No. 1108725N.

Publisher Copyright:
© John Benjamins Publishing Company.

Keywords

construction grammar
computational construction grammar
usage-based linguistics
computational modelling
learning construction grammars

Access to Document

10.1075/cf.23026.douLicence: CC BY

cf.23026.douFinal published version, 408 KBLicence: CC BY

Cite this

@article{6b0b11e6efc945a89c9a56c1d10dc094,

title = "The computational learning of construction grammars: State of the art and prospective roadmap",

abstract = "This paper documents and reviews the state of the art concerning computational models of construction grammar learning. It brings together prior work on the computational learning of form-meaning pairings, which has so far been studied in several distinct areas of research. The goal of this paper is threefold. First of all, it aims to synthesise the variety of methodologies that have been proposed to date and the results that have been obtained. Second, it aims to identify those parts of the challenge that have been successfully tackled and reveal those that require further research. Finally, it aims to provide a roadmap which can help to boost and streamline future research efforts on the computational learning of large-scale, usage-based construction grammars.",

keywords = "construction grammar, computational construction grammar, usage-based linguistics, computational modelling, learning construction grammars",

author = "Jonas Doumen and Schmalz, {Veronica Juliana} and Katrien Beuls and {Van Eecke}, Paul",

note = "Funding Information: The research reported in this paper was funded by the European Union\u2019s Horizon 2020 research and innovation programme under grant agreement No. 951846, the Flemish Government under the Onderzoeksprogramma Artifici\u00EBle Intelligentie (AI) Vlaanderen programme, the Walloon AI Flagship programme ARIAC, and the F.R.S.-FNRS - FWO WEAVE project HERMES I under grant numbers T002724F (F.R.S.-FNRS) and G0AGU24N (FWO). PVE was supported by a postdoctoral fellowship of the Research Foundation Flanders (FWO) with grant No. 75929. JD was funded by the imec.icon project COSMO (HBC.2018.0531) and the imec Smart Education covenant funding Edulab. VJS was funded through a doctoral fellowship awarded by the Research Foundation Flanders (FWO) with grant No. 1108725N. Publisher Copyright: {\textcopyright} John Benjamins Publishing Company.",

year = "2025",

doi = "10.1075/cf.23026.dou",

language = "English",

volume = "17",

journal = "Constructions and Frames",

issn = "1876-1933",

publisher = "John Benjamins Publishing Company",

number = "1",

}

TY - JOUR

T1 - The computational learning of construction grammars

T2 - State of the art and prospective roadmap

AU - Doumen, Jonas

AU - Schmalz, Veronica Juliana

AU - Beuls, Katrien

AU - Van Eecke, Paul

N1 - Funding Information: The research reported in this paper was funded by the European Union\u2019s Horizon 2020 research and innovation programme under grant agreement No. 951846, the Flemish Government under the Onderzoeksprogramma Artifici\u00EBle Intelligentie (AI) Vlaanderen programme, the Walloon AI Flagship programme ARIAC, and the F.R.S.-FNRS - FWO WEAVE project HERMES I under grant numbers T002724F (F.R.S.-FNRS) and G0AGU24N (FWO). PVE was supported by a postdoctoral fellowship of the Research Foundation Flanders (FWO) with grant No. 75929. JD was funded by the imec.icon project COSMO (HBC.2018.0531) and the imec Smart Education covenant funding Edulab. VJS was funded through a doctoral fellowship awarded by the Research Foundation Flanders (FWO) with grant No. 1108725N. Publisher Copyright: © John Benjamins Publishing Company.

PY - 2025

Y1 - 2025

N2 - This paper documents and reviews the state of the art concerning computational models of construction grammar learning. It brings together prior work on the computational learning of form-meaning pairings, which has so far been studied in several distinct areas of research. The goal of this paper is threefold. First of all, it aims to synthesise the variety of methodologies that have been proposed to date and the results that have been obtained. Second, it aims to identify those parts of the challenge that have been successfully tackled and reveal those that require further research. Finally, it aims to provide a roadmap which can help to boost and streamline future research efforts on the computational learning of large-scale, usage-based construction grammars.

AB - This paper documents and reviews the state of the art concerning computational models of construction grammar learning. It brings together prior work on the computational learning of form-meaning pairings, which has so far been studied in several distinct areas of research. The goal of this paper is threefold. First of all, it aims to synthesise the variety of methodologies that have been proposed to date and the results that have been obtained. Second, it aims to identify those parts of the challenge that have been successfully tackled and reveal those that require further research. Finally, it aims to provide a roadmap which can help to boost and streamline future research efforts on the computational learning of large-scale, usage-based construction grammars.

KW - construction grammar

KW - computational construction grammar

KW - usage-based linguistics

KW - computational modelling

KW - learning construction grammars

UR - http://www.scopus.com/inward/record.url?scp=85212972270&partnerID=8YFLogxK

U2 - 10.1075/cf.23026.dou

DO - 10.1075/cf.23026.dou

M3 - Article

VL - 17

JO - Constructions and Frames

JF - Constructions and Frames

SN - 1876-1933

IS - 1

ER -

The computational learning of construction grammars: State of the art and prospective roadmap

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

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

FWOAL1129: Syntactico-semantic generalisation operators for learning large-scale usage-based construction grammars

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

babel

Cite this

The computational learning of construction grammars: State of the art and prospective roadmap

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Projects

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

FWOAL1129: Syntactico-semantic generalisation operators for learning large-scale usage-based construction grammars

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

Datasets

babel

Cite this