Modelling Language Acquisition through Syntactico-Semantic Pattern Finding

Jonas Doumen, Katrien Beuls, Paul Van Eecke


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.
Anthology ID:
2023.findings-eacl.99
Volume:
Findings of the Association for Computational Linguistics: EACL 2023
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1347–1357
Language:
URL:
https://aclanthology.org/2023.findings-eacl.99
DOI:
10.18653/v1/2023.findings-eacl.99
Bibkey:
Cite (ACL):
Jonas Doumen, Katrien Beuls, and Paul Van Eecke. 2023. Modelling Language Acquisition through Syntactico-Semantic Pattern Finding. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1347–1357, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Modelling Language Acquisition through Syntactico-Semantic Pattern Finding (Doumen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-eacl.99.pdf
Dataset:
 2023.findings-eacl.99.dataset.zip
Video:
 https://aclanthology.org/2023.findings-eacl.99.mp4