Cognitive models of child word learning in general, and cross-situational models in particular, characterize the learner as a passive observer. But children are curious and actively participate in verbal and non-verbal communication, and often introduce new topics which parents are likely to follow up (Bloom et al., 1996). We investigate the potential impact of curiosity on word learning through a series of computational experiments. Our simulation results show that a curious learner who actively and curiously influences the language input it receives learns faster and more robustly, and reaches better performance.Published on: Proceedings of The 26th Architectures and Mechanisms for Language Processing Conference (AMLaP 2020)
ResourcesOn publisher website Read the Paper Code
Lieke Gelderloos, Alireza Mahmoudi Kamelabad, & Afra Alishahi (2020). Curiosity in self-supervised active word learning. In Proceedings of The 26th Architectures and Mechanisms for Language Processing Conference (AMLaP 2020). Universität Potsdam.
Download Bib File