A CONNECTIONIST MODEL OF THE ARABIC PLURAL SYSTEM

Connectionist accounts of inflectional morphology have focused on the domain of the English past tense in which the default process (add/ed/ ) reflects the process of suffixation adopted by the majority of forms in the language. Connectionist models exploit the imbalance between E nglish regular and irregular verbs when learning the past tense and wh en responding to novel forms in a default fashion. Not all inflectiona l systems have a default which is characterised by a majority of forms in the language. The Arabic plural system has been cited as one such system where a minority default process operates-the ''sound'' plural in Arabic applies to only a minority of the forms in the lexicon, yet it appears to adopt the role of a default for novel nouns. We contrast two types of default process that might lead to this behaviour, a sym bolic default and a distributional default. We provide a detailed anal ysis of the phonological similarity structure of the Arabic plural sys tem and conclude that it is unlikely the distribution of singular Arab ic nouns can support a distributional default for the sound plural. Ne vertheless, classification networks and pattern association networks p erform surprisingly well at the task of learning the Arabic plural and generalising to unseen Arabic nouns. In fact, the performance of a ne ural network classifier exceeds the performance of a symbolic hybrid ' 'rule-associative'' model even when the latter is optimised for correc t classification. We conclude that the default rule is redundant, sinc e generalisation to novel forms is more accurately predicted by the si milarity structure in the phonological space of Arabic nouns alone. Fi nally, we present a set of empirical predictions for children's; acqui sition of the Arabic plural system, derived from the network simulatio ns.