ABSTRACT
INTRODUCTION The standard position in both Al and linguistics, that natural language processing (NLP) is highly symbolic in nature, has recently come under critical review (e.g. Churchland & Sejnowski, 1989; Dreyfus & Dreyfus, 1988; Reeke & Edelman, 1988; Smolensky, 1988b). Researchers in the distributed connectionist systems (DCS) camp have built architectures in which language-related tasks are reformulated as mapping tasks that are fundamentally associative in nature. Examples are: mapping syntax to semantics (McClelland & Kawamoto, 1986); mapping present to past tense (Rumelhart & McClelland, 1986b); translating language LI to L2 (Allen, 1986); and mapping orthography to morphemes (Sejnowski & Rosenberg, 1987). What motivates these researchers are the useful features displayed by distributed connectionist networks, namely: (1) graceful degradation to noise and damage; (2) automatic learning and generalisation to novel inputs; (3) massive parallelism; (4) self-organisation and reconstructive memory; and (5) increased neural plausibility, including lesionability (Rumel hart and McClelland, 1986c; Smolensky, 1988a).
