Curious Topics: A Curiosity-Based Model of First Language Word Learning

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


This paper investigates whether a curiosity-based strategy could be beneficial to word learning. Children are active conversation partners and exert considerable influence over the topics that are discussed in conversation with their parents. As the choice of topics is likely to be intrinsically motivated, a formalization of curiosity is implemented in a word learning model. The model receives annotated Flickr30k Entities images as input, and is trained in two conditions. In the curious condition, the model chooses objects to talk about from the scene according to the curiosity mechanism, whereas in the random condition, the model receives randomly chosen objects as input. The goal of this study is to show how a curious, active choice of topics by a language learner improves word learning compared to random selection. Curiosity is found to make word learning faster, increase robustness, and lead to better accuracy.
Original languageEnglish
Title of host publicationProceedings of the 41st Annual Conference of the Cognitive Science Society
Place of PublicationMontreal
PublisherCognitive Science Society
Publication statusPublished - Jul 2019
EventAnnual Meeting of the Cognitive Science Society 2019: Creativity + Cognition + Computation - Palais des Congrès , Montreal, Canada
Duration: 24 Jul 201927 Jul 2019
Conference number: 41


ConferenceAnnual Meeting of the Cognitive Science Society 2019
Abbreviated titleCogSci 2019
Internet address

Cite this