Title

How to Disassemble Alphabetical Processions - Morphological Treatment of Unknown Words

Author(s)

Stephan Bopp, Sandro Pedrazzini, Elisabeth Maier

Canoo Engineering AG, Basel, Switzerland

Session

P14-W

Abstract

This paper describes an approach how to integrate the decomposition of non-lexicalized word compounds and derivations into the morphological analyzers of a NLP product line. The component employs word formation rules and filtering techniques to decompose words, which are not contained in the underlying dictionary database, thereby increasing the average word recognition rate of the morphological analyzers from 90.6% to 95.4%.

Keyword(s)

morphological analysis, morphological analyzers, unknown words, NLP-products

Language(s) German, Italian, English
Full Paper

54.pdf