Usage-based Grammar Learning as Insight Problem Solving

Abstract

We report on computational experiments in which a learning agent incrementally acquires grammar from a tutoring agent through situated embodied interactions. The learner is able to detect impasses in routine language processing, such as missing a grammatical construction to integrate a word in the rest of the sentence structure, to move to a meta-level to repair these impasses, primarily based on semantics, and to then expand or restructure his grammar using insights gained from repairs. The paper proposes a cognitive architecture able to support this kind of insight learning and tests it on a grammar learning task.