Generalization Performance Of Backpropagation Learning On A Syllabification Task
Walter M. P. Daelemans, Antal van den Bosch · 1992
We investigated the generalization capabilities of backpropagation learning in feed-forward and recurrent feed-forward connectionist networks on the assignment of syllable boundaries to orthographic representations in Dutch (hyphenation). This is a difficult task because phonological and morphological constraints interact, leading to ambiguity in the input patterns. We compared the results to different symbolic pattern matching approaches, and to an exemplar-based generalization scheme, related to a k-nearest neighbour approach, but using a similarity metric weighed by the relative information entropy of positions in the training patterns. Our results indicate that the generalization performance of backpropagation learning for this task is not better than that of the best symbolic pattern matching approaches, and of exemplar-based generalization. 1 BACKGROUND There is a marked difference between the rich inventory of representational and control structures used in "symbolic" approache...