Ronan G. Reilly

Preliminary Results On Speech Signal Segmentation With Recurrent Neural Networks (2008)

Antonio Rubio, Ronan G. Reilly

A continuous speech recognition system has to explore the search space with the only information given by the probabilities provided by a set of hidden Markov models representing the different sounds...

Reviewed by (2007)

Ronan G. Reilly, Noel E. Sharkey, James Henderson

With the growing popularity of statistical approaches to natural language processing, it is natural to consider how connectionist techniques for learning and using soft constraints might be...

Evolution of symbolisation: Signposts to a bridge between connectionist and symbolic systems (2000)

Ronan G. Reilly

Abstract. This paper describes recent attempts to understand the evolution of language in humans and argues that useful lessons can be learned from this analysis by designers of hybrid...

A connectionist model of some aspects of anaphor resolution (1984)

Ronan G. Reilly

This paper describes some recent developments in language processing involving computational models which more closely resemble the brain in both structure and function. These models employ a large...