Cascadilla Proceedings Project: Paper 1467


Home page

List of proceedings

Enter a document #:
Enter search terms:




Info for readers

Info for authors

Info for editors

Info for libraries



Order form

Shopping cart

Proceedings of the 25th West Coast Conference on Formal Linguistics
edited by Donald Baumer, David Montero, and Michael Scanlon

ISBN 1-57473-415-6 library binding
vii+461 pages
publication date: 2006
published by Cascadilla Proceedings Project, Somerville, MA, USA

Table of contents



Abstract

Jason Riggle
Using Entropy to Learn OT Grammars from Surface Forms Alone
346-353 (complete pdf)

The problem of ranking Optimality Theoretic constraints in a fashion that is consistent with a given set of (input, output) pairs has been solved with a variety of algorithms (cf. Tesar and Smolensky 2002, Boersma and Hayes 1999). The real-world problem of learning from outputs alone, however, still presents a host of challenges. Chief among these is the fact that there are often several (possible-input, possible-grammar) pairs that are consistent with a given set of surface forms. This paper explores strategies for learning from surface forms that use information-theoretic measures of the randomness (entropy) of the input set associated with each grammar hypothesis as a heuristic to select the grammars that maximally encode any observed patterns. This represents a straightforward use of the Richness of the Base Hypotheses (Smolensky 1996) to avoid encoding observed patterns as accidental patterns in the lexicon.


Copyright © 2006 Cascadilla Proceedings Project. All rights reserved. To request permission to copy any elements from our pages, or to send comments or questions about our pages, please write to webmaster@cascadilla.com and make sure to provide the URL of the particular page. This page last updated 28 November 2006.