[Author Login]
Title:Learning Phonotactic Distributions
Authors:Alan Prince, Bruce Tesar
Abstract:Learning Phonotactic Distributions

Alan Prince & Bruce Tesar
Dept. of Linguistics and Center for Cognitive Science

Rutgers University

Many essentials of a language's phonology can be learned from
distributional evidence, in the absence of detailed morphological
analysis. But distributional learning from positive evidence
encounters the subset problem in full force. Here we explore an
approach in which the learning algorithm, based on the error-
driven variant of Recursive Constraint Demotion (RCD: Tesar 1995,
Tesar & Smolensky 1998), is persistently biased to place
markedness constraints as high as possible, but aims to place
faithfulness constraint as low as possible. The learner seeks
only to reproduce the output from identical input, avoiding all
concern with nontrivial underlying forms; under the M>>F bias
this results in significant learning. (Hayes 1999 independently
develops a similar approach from the same basic assumptions.)
We introduce an explicit measure of the degree to which a
hierarchy possesses M>>F structure, and we investigate the
consequences of trying to maximize this measure by low placement
of F in suitably biased versions of RCD. We argue that existing
proposals by which M>>F structure is carried over from an initial
state through a learning procedure blind to the M/F distinction,
as in the different conceptions of Smolensky 1996 and Ito &
Mester 1998, cannot accomplish this goal successfully, as they
are currently understood. We conclude that Biased Constraint
Demotion (BCD) must be used by the learner at each step.
The key issue is deciding which F to rank when there is more
than one F constraint to choose from. We suggest that the main
desideratum is the 'freeing up' of further M constraints for
ranking, though we also show that such decisions have further
consequences downstream for the resultant hierarchy that may
motivate a certain kind of 'look ahead' in the decision-making
process. We also consider the issue of the ranking of special-
general pairs of faithfulness constraints, arguing that the
matter cannot be resolved by examining the structure of
constraints in isolation. We show that special/general relations
can be derived mid-hierarchy, on the one hand, and on the other,
can arise between constraints that appear to be independent. We
note that in sharp contrast to the faithfulness situation,
special/general relations between markedness constraints are
handled automatically by BCD; this provides learning-theoretic
motivation for resolving the positional markedness vs. positional
faithfulness controversy (Beckman 1998, Zoll 1998) and for deeper
scrutiny of faithfulness theory as a whole.
Type:Paper/tech report
Area/Keywords:Learnability,Formal Analysis,Phonology,Psycholinguistics
Article:Version 1