Deep daxes: Mutual exclusivity arises through both learning biases and pragmatic strategies in neural networks
This work addresses how computational models can mimic children's word learning biases, offering insights for cognitive research and model performance in tasks requiring mutual exclusivity.
The paper investigated how neural networks develop mutual exclusivity in word learning, finding that constraints in learning and selection foster this behavior when words compete for lexical meaning, with performance improvements observed on both symbolic and image data.
Children's tendency to associate novel words with novel referents has been taken to reflect a bias toward mutual exclusivity. This tendency may be advantageous both as (1) an ad-hoc referent selection heuristic to single out referents lacking a label and as (2) 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. To this end, we evaluate neural networks' on both symbolic data and, as a first, on large-scale image data. 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.