PatPho: A phonological pattern generator for neural networks

Ping Li, Brian Macwhinney

Research output: Contribution to journalArticlepeer-review

39 Scopus citations


Much of the power of neural network modeling for language use and acquisition derives from a reliance on statistical regularities implicit in the phonological properties of words. Researchers have devised several methods for representing the phonology of words, but these methods are often either unable to represent realistically sized lexicons or inadequate in the ways they represent individual words. In this paper, we present a new phonological pattern generator (PatPho) that allows connectionist modelers to derive accurate phonological representations of the English lexicon. PatPho not only generates phonological patterns that can scale up to realistically sized lexicons, but also accurately and parsimoniously captures the similarity structures of the phonology of monosyllabic and multisyllabic words.

Original languageEnglish (US)
Pages (from-to)408-415
Number of pages8
JournalBehavior Research Methods, Instruments, and Computers
Issue number3
StatePublished - Aug 2002

All Science Journal Classification (ASJC) codes

  • Experimental and Cognitive Psychology
  • Psychology (miscellaneous)
  • General Psychology


Dive into the research topics of 'PatPho: A phonological pattern generator for neural networks'. Together they form a unique fingerprint.

Cite this