Modelling Language Acquisition through Syntactico-Semantic Pattern Finding

Jonas Doumen, Katrien Beuls, Paul Van Eecke

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

32 Téléchargements (Pure)

Résumé

Usage-based theories of language acquisition have extensively documented the processes by which children acquire language through communicative interaction. Notably, in 'Constructing A Language' (2003), Tomasello 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 distill 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 that models how the slots of the item-based constructions can be filled by the lexical constructions. 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, thereby paving the way for building truly intelligent agents that are capable of human-like communication.
langue originaleAnglais
titreFindings of the Association for Computational Linguistics: EACL 2023
EditeurAssociation for Computational Linguistics
Pages1347–1357
Etat de la publicationPublié - 2023
EvénementThe 17th Conference of the European Chapter of the Association for Computational Linguistics - Dubrovnik, Croatie
Durée: 2 mai 20234 mai 2023
Numéro de conférence: 17
https://2023.eacl.org

Une conférence

Une conférenceThe 17th Conference of the European Chapter of the Association for Computational Linguistics
Titre abrégéEACL
Pays/TerritoireCroatie
La villeDubrovnik
période2/05/234/05/23
Adresse Internet

Empreinte digitale

Examiner les sujets de recherche de « Modelling Language Acquisition through Syntactico-Semantic Pattern Finding ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation