Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks
- Kristina Gulordava, Shift Technology, Paris, France
- Thomas Brochhagen, Universitat Pompeu Fabra, Barcelona, Spain
- Gemma Boleda, Universitat Pompeu Fabra, Barcelona, Spain
AbstractChildren's tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency can be advantageous both as an ad-hoc referent selection heuristic to single out referents lacking a label, and as an organizing principle of lexical acquisition. This paper investigates under which circumstances cross-situational neural models can come to exhibit analogous behavior to children, focusing on these two possibilities and their interaction. We find that constraints in both learning and selection can foster mutual exclusivity, as long as they put words in competition for lexical meaning. For computational models, these findings clarify the role of available options for better performance in tasks where mutual exclusivity is advantageous. For cognitive research, they highlight latent interactions between word learning, referent selection mechanisms, and the structure of stimuli of varying complexity: symbolic and visual.