Visually Grounded Speech Models Have a Mutual Exclusivity Bias
Open Access
- 4 June 2024
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 12, 755-770
Abstract
When children learn new words, they employ constraints such as the mutual exclusivity (ME) bias: A novel word is mapped to a novel object ratherKeywords
All Related Versions
This publication has 47 references indexed in Scilit:
- The role of developmental change and linguistic experience in the mutual exclusivity effectCognition, 2020
- Jointly Discovering Visual Objects and Spoken Words from Raw Sensory Input2018
- Microsoft COCO: Common Objects in Context2014
- The Buckeye corpus of conversational speech: labeling conventions and a test of transcriber reliabilitySpeech Communication, 2005
- How language acquisition builds on cognitive developmentTrends in Cognitive Sciences, 2004
- Use of the mutual exclusivity assumption by young word learnersCognitive Psychology, 2003
- The development of a word-learning strategyCognition, 2003
- Object Recognition and Object Segregation in 4.5-Month-Old InfantsJournal of Experimental Child Psychology, 2001
- Infants′ Detection of the Sound Patterns of Words in Fluent SpeechCognitive Psychology, 1995
- Children's use of mutual exclusivity to constrain the meanings of wordsCognitive Psychology, 1988