A back-propagation network with recurrent connections can successfully model many aspects of human spoken word recognition [1] [2]. However, the network is unable to revise its decisions in the light of subsequent context. TRACE [3] , on the other hand, manages to deal appropriately with following context but only by using a highly implausible architecture that fails to account for some important experimental results. A new model is presented which combines the more desirable properties of these two models. In contrast to TRACE the model is entirely bottom-up and can readily perform simulations with vocabularies of tens of thousands of words.
Cite as: Norris, D. (1991) Rewiring lexical networks on the fly. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 117-120, doi: 10.21437/Eurospeech.1991-25
@inproceedings{norris91_eurospeech,
author={Dennis Norris},
title={{Rewiring lexical networks on the fly}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={117--120},
doi={10.21437/Eurospeech.1991-25}
}