Grounded Learning of Grammatical Constructions
Nancy Chang, Tiago V. Maia · 2001
We describe a model of grammar learning in which all linguistic units are grounded in rich conceptual rep-resentations, and larger grammatical constructions in-volve relational mappings between form and meaning that are built up from smaller (e.g., lexical) construc-tions. The algorithm we describe for acquiring these grammatical constructions consists of three separate but interacting processes: an analysis procedure that uses the current set of constructions to identify mappings be-tween an utterance and its accompanying situation; a hypothesis procedure that creates new constructions to account for remaining correlations between these two domains; and reorganization processes that generalize existing constructions on the basis of similarity and co-occurrence. The algorithm is thus grounded not only in the twin poles of form and meaning but also, more im-portantly, in the relational mappings between the two.