Partially Improved Subsequence Discovery Algorithm for Sequence Matching
A. D. Pathak, S. J. Karale · 2013
This article describes an Improved technique for the sub sequence discovery algorithm used for natural language processing in question answering system for matching user text input in natural language processing against an existing knowledge base, consisting of semantically described words or phrases. Most common methods & techniques of natural language processing are overviewed and their main problems are outlined. A sequence matching with subsequence analysis algorithm is analyzed and improvements are done which deals with the problems of exact matching,change in custom spelling errors as well as the improvement in the performance metric of the similarity matching.Popular approaches that solve this problem include stemming, lemmatization and various distance functions,sequence matching techniques are analysed to get the better possible technique for solving the problems with higher accuracy. Then the major components of the similarity measure are defined and the computation of concurrence and dispersion measure is presented. Results of the algorithms performance on a test set are then analysed.