Bayesian learning over conflicting data: predictions for language change

Authors:
Rebecca Morley
Affiliations:
Johns Hopkins University, Baltimore, MD
Venue:
SigMorPhon '08 Proceedings of the Tenth Meeting of ACL Special Interest Group on Computational Morphology and Phonology
Year:
2008

Citing 4
Cited 0

Stochastic Complexity in Statistical Inquiry Theory

Stochastic Complexity in Statistical Inquiry Theory
Machine Learning

Machine Learning
A selectionist theory of language acquisition

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Richness of the base and probabilistic unsupervised learning in optimality theory

SIGPHON '06 Proceedings of the Eighth Meeting of the ACL Special Interest Group on Computational Phonology and Morphology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is an analysis of the claim that a universal ban on certain ('anti-markedness') grammars is necessary in order to explain their non-occurrence in the languages of the world. To assess the validity of this hypothesis I examine the implications of one sound change (a ə) for learning in a specific phonological domain (stress assignment), making explicit assumptions about the type of data that results, and the learning function that computes over that data. The preliminary conclusion is that restrictions on possible end-point languages are unneeded, and that the most likely outcome of change is a lexicon that is inconsistent with respect to a single generating rule.