Publications – Fluid Construction Grammar

69 entries « ‹ 1 of 2 › »

2024

Liesbet De Vos Jens Nevens, Paul Van Eecke ; Beuls, Katrien

Construction grammar and procedural semantics for human-interpretable grounded language processing Journal Article

Linguistics Vanguard, (0), 2024.

Abstract | BibTeX | Tags: Computational Construction Grammar, Fluid Construction Grammar, grounded language understanding, procedural semantics

@article{de2024construction,
title = {Construction grammar and procedural semantics for human-interpretable grounded language processing},
author = {Liesbet De Vos, Jens Nevens, Paul Van Eecke and Katrien Beuls},
year = {2024},
date = {2024-03-15},
journal = {Linguistics Vanguard},
number = {0},
abstract = {Groundedlanguageprocessingisacrucialcomponentinmanyartificialintelligencesystems,asitallows agents to communicate about their physical surroundings. State-of-the-art approaches typically employ deep learning techniques that perform end-to-end mappings between natural language expressions and representations grounded in the environment. Although these techniques achieve high levels of accuracy, they are often criticized for their lack of interpretability and their reliance on large amounts of training data. As an alternative, we propose a fully interpretable, data-efficient architecture for grounded language processing. The architecture is based on two main components. The first component comprises an inventory of human-interpretable concepts learned through task-based communicative interactions. These concepts connect the sensorimotor experiences of an agent to meaningful symbols that can be used for reasoning operations. The second component is a computational con- struction grammar that maps between natural language expressions and procedural semantic representations. These representations are grounded through their integration with the learned concepts. We validate the archi- tecture using a variation on the CLEVR benchmark, achieving an accuracy of 96 %. Our experiments demonstrate that the integration of a computational construction grammar with an inventory of interpretable grounded con- cepts can effectively achieve human-interpretable grounded language processing in the CLEVR environment.},
keywords = {Computational Construction Grammar, Fluid Construction Grammar, grounded language understanding, procedural semantics},
pubstate = {published},
tppubtype = {article}
}

Beuls, Katrien; Van Eecke, Paul

Construction Grammar and Artificial Intelligence Book Chapter Forthcoming

Fried, Mirjam; Nikiforidou, Kiki (Ed.): The Cambridge Handbook of Construction Grammar, Cambridge University Press, Cambridge, Forthcoming.

Abstract | BibTeX | Tags: Fluid Construction Grammar

2023

Doumen, Jonas; Beuls, Katrien; Van Eecke, Paul

Modelling Language Acquisition through Syntactico-Semantic Pattern Finding Inproceedings

Findings of the Association for Computational Linguistics: EACL 2023, pp. 1317-1327, Association for Computational Linguistics, 2023.

Abstract | Links | BibTeX | Tags: Fluid Construction Grammar

@inproceedings{doumen2023modelling,
title = {Modelling Language Acquisition through Syntactico-Semantic Pattern Finding},
author = {Jonas Doumen and Katrien Beuls and Paul {Van Eecke}},
url = {https://aclanthology.org/2023.findings-eacl.99/},
year = {2023},
date = {2023-05-01},
booktitle = {Findings of the Association for Computational Linguistics: EACL 2023},
pages = {1317-1327},
publisher = {Association for Computational Linguistics},
abstract = {Usage-based theories of language acquisition have extensively documented the processes by which children acquire language through communicative interaction. Notably, Tomasello (2003) distinguishes two main cognitive capacities that underlie human language acquisition: intention reading and pattern finding. Intention reading is the process by which children try to continuously reconstruct the intended meaning of their interlocutors. Pattern finding refers to the process that allows them to distil linguistic schemata from multiple communicative interactions. Even though the fields of cognitive science and psycholinguistics have studied these processes in depth, no faithful computational operationalisations of these mechanisms through which children learn language exist to date. The research on which we report in this paper aims to fill part of this void by introducing a computational operationalisation of syntactico-semantic pattern finding. Concretely, we present a methodology for learning grammars based on similarities and differences in the form and meaning of linguistic observations alone. Our methodology is able to learn compositional lexical and item-based constructions of variable extent and degree of abstraction, along with a network of emergent syntactic categories. We evaluate our methodology on the CLEVR benchmark dataset and show that the methodology allows for fast, incremental and effective learning. The constructions and categorial network that result from the learning process are fully transparent and bidirectional, facilitating both language comprehension and production. Theoretically, our model provides computational evidence for the learnability of usage-based constructionist theories of language acquisition. Practically, the techniques that we present facilitate the learning of computationally tractable, usage-based construction grammars, which are applicable for natural language understanding and production tasks.},
keywords = {Fluid Construction Grammar},
pubstate = {published},
tppubtype = {inproceedings}
}

Beuls, Katrien; Van Eecke, Paul

Fluid Construction Grammar: State of the Art and Future Outlook Inproceedings

Proceedings of the First International Workshop on Construction Grammars and NLP (CxGs+NLP, GURT/SyntaxFest 2023), pp. 41-50, 2023.

Links | BibTeX | Tags: Fluid Construction Grammar