Department of Electronic Systems Engineering, University of Essex, Wivenhoe Park, Colchester CO4 3SQ, United Kingdom
Abstract:
A new method of searching large dictionaries given uncertain inputs is described, based on the lazy evaluation of a syntactic neural network (SNN). The new method is shown to significantly outperform a conventional trie-based method for large dictionaries (e.g. in excess of 100,000 entries). Results are presented for the problem of recognising UK postcodes using dictionary sizes of up to 1 million entries. Most significantly, it is demonstrated that the SNN actually gets faster as more data is loaded into it.