Connectionist modelling of Chinese character pronunciation based on foveal splitting

Janet Hui-wen Hsiao, Richard Shillcock

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We describe a connectionist model designed to reflect some of the anatomy of the visual pathways, notably the precise division of the human fovea and its subsequent contralateral projection to the cortex. The model was trained on a realistically large-scale problem, mapping between Chinese orthography and phonology. This split-fovea model replicated the interaction between character regularity and frequency that has been found in Chinese phonetic compound naming tasks. It also provided cross-language support for the hemispheric desynchronization account of dyslexia. Finally, the model predicted different regularity effects between characters with different phonetic radical positions.
Original languageEnglish
Title of host publicationProceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society
Pages601-606
Number of pages6
Publication statusPublished - 2004

Fingerprint Dive into the research topics of 'Connectionist modelling of Chinese character pronunciation based on foveal splitting'. Together they form a unique fingerprint.

Cite this