Infinite RAAM: A Principled Connectionist Basis for Grammatical Competence
Simon D. Levy, Ofer Melnik, Jordan B. Pollack · eScholarship (California Digital Library) · 2000
This paper presents Infinite RAAM (IRAAM), a new fusion of recurrent neural networks with fractal geometry, allowing us to understand the behavior of these networks as dynamical systems. Our recent work with IRAAMs has shown that they are capable of generating the context-free (non-regular) language a n b n for arbitrary values of n. This paper expands upon that work, showing that IRAAMs are capable of generating syntactically ambiguous languages but seem less capable of generating certain context-free constructions that are absent or disfavored in natural languages. Together, these demonstrations support our belief that IRAAMs can provide an explanatorily adequate connectionist model of grammatical competence in natural language. Natural Language Issues In an early and extremely influential paper, Noam Chomsky (1956) showed that natural languages (NL's) cannot be modeled by a finite-state automaton, because of the existence of center-embedded constructions. A second ...