<OT> New Posting: ROA-1055

[roa at ruccs.rutgers.edu]

ROA 1055-1109

Phonotactic learning without a priori constraints: A connectionist analysis of Arabic cooccurrence restrictions

John Alderete <alderete at sfu.ca>
Stefan Frisch <safrisch at indiana.edu>

Direct link: http://roa.rutgers.edu/view.php3?roa=1055


Abstract:
In this article, we develop a connectionist model of learning
phonotactics and apply it to the problem of learning root
cooccurrence restrictions in Arabic. Two types of connectionist
networks are developed: a multilayer network with a hidden
layer and a single layer network with recurrent connections.
They are both shown to classify Arabic words and nonwords
in ways that are qualitatively parallel to psycholinguistic
studies of Arabic. In these networks, units and connections
act like soft constraints in the computation of acceptability
scores. Because these constraints are malleable and can
change gradually over time, the networks learn phonotactic
generalizations without requiring the prior existence of
the exact constraints responsible for phonotactics, a fact
that sets this model apart from many phonotactic learners.

Comments: 
Keywords: phonotactics, phonotactic learning, gradient acceptability, computational language learning, connectionism, artificial neural networks, psycholinguistics, Arabic
Areas: Phonology,Computation,Formal Analysis
Type: Manuscript

Direct link: http://roa.rutgers.edu/view.php3?roa=1055