Learning the meanings of function words from grounded language using a visual question answering model

arXiv:2308.08628v3 Announce Type: replace
Abstract: Interpreting a seemingly-simple function word like "or", "behind", or "more" can require logical, numerical, and relational reasoning. How are such words learned by children? Prior acquisition theories have often relied on positing a foundation of innate knowledge. Yet recent neural-network based visual question answering models apparently can learn to use function words as part of answering questions about complex visual scenes. In this paper, we study what these models learn about function words, in the …

abstract acquisition arxiv children cs.cl foundation function knowledge language network numerical prior question question answering reasoning relational simple type visual word words