Toward a connectionist model of recursion in human linguistic performance

Naturally occurring speech contains only a limited amount of complex recursive structure, and this is re ected in the empirically documented di culties that people experience when processing such structures. We present a connectionist model of human performance in processing recursive language structures. The model is trained on simple arti cial languages. We nd that the qualitative performance pro le of the model matches human behavior, both on the relative di culty of center-embedded and cross-dependency, and between the processing of these complex recursive structures and right-branching recursive constructions. We analyze how these di erences in performance are re ected in the internal representations of the model by performing discriminant analyses on these representation both before and after training. Furthermore, we show how a network trained to process recursive structures can also generate such structures in a probabilistic fashion. This work suggests a novel explanation of people's limited recursive performance, without assuming the existence of a mentally represented competence grammar allowing unbounded recursion. 1