Morphological Analysis Using Linguistically Motivated Decomposition of Unknown Words

Bopp, Stephan and Pedrazzini, Sandro (2009) Morphological Analysis Using Linguistically Motivated Decomposition of Unknown Words. In: Mahlow, Cerstin and Piotrowski, Michael, (eds.) State of the Art in Computational Morphology, Workshop on Systems and Frameworks for Computational Morphology. Communications in Computer and Information Science (41). Springer, Zurich. ISBN 978-3-642-04130-3

Full text not available from this repository.

Abstract

Integrating the decomposition of unknown morphologically complex words can enhance the recognition rates of morphological analyzers. Using linguistically motivated strategies for this decomposition leads to even more expressive results. The approach described here uses word formation rules and filtering techniques 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.Integrating the decomposition of unknown morphologically complex words can enhance the recognition rates of morphological analyzers. Thereby uUsing linguistically motivated strategies for this decomposition leads to even more expressive results. The approach described here uses word formation rules and filtering techniquefilters to analyze and decompose words that are not contained in the underlying dictionary databaseused for the text analysis. The average recognition rate of the analyzers increases from 91% to 95,4%.

Actions (login required)

View Item View Item