Morphological analysis using linguistically motivated decomposition of unknown words

Abstract

Integrating the decomposition of unknown morphologically complex words can enhance the recognition rates of morphological analyzers. Using linguisti cally motivated strategies for this decomposition leads to even more expressive re sults. The approach described here uses word formation rules and filtering tech niques to analyze and decompose words that are not contained in the underlying dictionary database. The average recognition rate of our German analyzers, applied to our test corpus, increased from 91% to 95,4%. Together with the current implementation, further future decomposition strategies will be presented. © 2009 Springer-Verlag.