Graded Grammaticality in Prediction Fractal Machines
S. H. Parfitt, Peter Tiňo, Georg Dorffner · Neural Information Processing Systems · 1999
We introduce a novel method of constructing language models, which avoids some of the problems associated with recurrent neural networks. The method of creating a Prediction Fractal Machine (PFM) [1] is briefly described and some experiments are presented which demonstrate the suitability of PFMs for language modeling. PFMs distinguish reliably between minimal pairs, and their behavior is consistent with the hypothesis [4] that wellformedness is 'graded' not absolute. A discussion of their potential to offer fresh insights into language acquisition and processing follows.