Multimodal Semantic Learning from Child-Directed Input
Lazaridou,Angeliki Chrupala,Grzegorz Fernández,Raquel Baroni,Marco
Lazaridou,Angeliki
Chrupala,Grzegorz
Fernández,Raquel
Baroni,Marco
Abstract
Children learn the meaning of words by being exposed to perceptually rich situations (linguistic discourse, visual scenes, etc). Current computational learning models typically simulate these rich situations through impoverished symbolic approximations. In this work, we present a distributed word learning model that operates on child-directed speech paired with realistic visual scenes. The model integrates linguistic and extra-linguistic information (visual and social cues), handles referential uncertainty, and correctly learns to associate words with objects, even in cases of limited linguistic exposure.
Description
Date
2016-06
Journal Title
Journal ISSN
Volume Title
Publisher
Association for Computational Linguistics
Research Projects
Organizational Units
Journal Issue
Keywords
Citation
Lazaridou, A, Chrupala, G, Fernández, R & Baroni, M 2016, Multimodal Semantic Learning from Child-Directed Input. in Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, pp. 387-392, North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, United States, 12/06/16. < http://clic.cimec.unitn.it/marco/publications/lazaridou-etal-multimodal-learning-from-cdi-naacl2016.pdf >
License
info:eu-repo/semantics/openAccess