Learning Orthographic Structure With Sequential Generative Neural Networks

Alberto Testolin, Ivilin Stoianov, Alessandro Sperduti, Marco Zorzi

Research output: Contribution to journalArticlepeer-review

Abstract

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain.

Original languageEnglish
JournalCognitive Science
DOIs
Publication statusAccepted/In press - 2015

Keywords

  • Connectionist modeling
  • Generative models
  • Orthographic structure
  • Probabilistic graphical models
  • Recurrent neural networks
  • Restricted Boltzmann machines
  • Statistical sequence learning
  • Unsupervised learning

ASJC Scopus subject areas

  • Language and Linguistics
  • Artificial Intelligence
  • Cognitive Neuroscience
  • Experimental and Cognitive Psychology

Fingerprint

Dive into the research topics of 'Learning Orthographic Structure With Sequential Generative Neural Networks'. Together they form a unique fingerprint.

Cite this