Spatio-Temporal Graph Neural Networks for Infant Language Acquisition Prediction

Roxburgh, Andrew ORCID: 0000-0003-1333-5654, Grasso, Floriana ORCID: 0000-0001-8419-6554 and R. Payne, Terry ORCID: 0000-0002-0106-8731 (2025) Spatio-Temporal Graph Neural Networks for Infant Language Acquisition Prediction In: 31st International Conference on Neural Information Processing (ICONIP2024), 2024-12-2 - 2024-11-6, Auckland, New Zealand.

PDF ICONIP2024_paper_3471-submitted.pdf - Submitted version Download (926kB) | Preview

Abstract

Predicting the words that a child is going to learn next can be useful for boosting language acquisition, and such predictions have been shown to be possible with both neural network techniques (looking at changes in the vocabulary state over time) and graph model (looking at data pertaining to the relationships between words). However, these models do not fully capture the complexity of the language learning process of an infant when used in isolation. In this paper, we examine how a model of language acquisition for infants and young children can be constructed and adapted for use in a Spatio-Temporal Graph Convolutional Network (STGCN), taking into account the different types of linguistic relationships that occur during child language learning. We introduce a novel approach for predicting child vocabulary acquisition, and evaluate the efficacy of such a model with respect to the different types of linguistic relationships that occur during language acquisition, resulting in insightful observations on model calibration and norm selection. An evaluation of this model found that the+ mean accuracy of models for predicting new words when using sensorimotor relationships (0.733) and semantic relationships (0.729) were found to be superior to that observed with a 2-layer Feedforward neural network. Furthermore, the high recall for some relationships suggested that some relationships (e.g. visual) were superior in identifying a larger proportion of relevant words that a child should subsequently learn than others (such as auditory).

Item Type:	Conference Item (Unspecified)
Uncontrolled Keywords:	46 Information and Computing Sciences, 4611 Machine Learning, Basic Behavioral and Social Science, Pediatric Research Initiative, Behavioral and Social Science, Machine Learning and Artificial Intelligence, Bioengineering
Divisions:	Faculty of Science & Engineering Faculty of Science & Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	05 Nov 2024 08:15
Last Modified:	15 Jan 2026 06:54
DOI:	10.1007/978-981-96-6606-5_10
Related Websites:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3187060
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.