Representation , Learning , Generalization and Damage in Neural Network Models of Reading Aloud

@inproceedings{Bullinaria1995RepresentationL,
  title={Representation , Learning , Generalization and Damage in Neural Network Models of Reading Aloud},
  author={John A. Bullinaria},
  year={1995}
}
We present a new class of neural network models of reading aloud based on Sejnowski & Rosenberg’s NETtalk. Unlike previous models, they are not restricted to mono-syllabic words, require no complicated inputoutput representations such as Wickelfeatures and require no preprocessing to align the letters and phonemes in the training data. The best cases are able to achieve perfect performance on the Seidenberg & McClelland training corpus (which includes many irregular words) and in excess of 95… CONTINUE READING
11 Extracted Citations
73 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 73 references

Models of Reading Aloud: Dual-Route and Parallel-Distributed-Processing Approaches

  • M. Coltheart, Curtis, P. B. Atkins, M. Haller
  • Psychological Review,
  • 1993
Highly Influential
11 Excerpts

Acquisition and use of spelling-sound information in reading

  • J. Backman, M. Bruck, M. Hébert, M. Seidenberg
  • Journal of Experimental Child Psychology,
  • 1984
Highly Influential
6 Excerpts

Computational analysis of present day AmericanEnglish,, Providence, RI

  • H. Kucera, W. N. Francis
  • 1967
Highly Influential
13 Excerpts

Neural Network Models of Reading Without Wickelfeatures

  • J. A. Bullinaria
  • Proceedings of the 2nd Neural Computation and…
  • 1993
Highly Influential
13 Excerpts

Conspiracy Effects in Word Pronunciation

  • R. Taraban, J. L. McClelland
  • Journal of Memory and Language,
  • 1987
Highly Influential
6 Excerpts

Similar Papers

Loading similar papers…