A linguistic bootstrapping approach to the extraction of term candidates from German text

Abstract

This paper deals with computational linguistic tools and methods for the extraction of raw material for terminological glossaries from machine-readable text. We concentrate on monolingual German term candidates, and only briefly hint at tools and procedures for the creation of bilingual glossaries. Most of the examples we use to illustrate methods and results of our work come from technical texts provided by the translation services of Daimler Chrysler AG1 and from legal texts made available by the European Academy in Bozen, Sudtirol. The Academy is working on translations of legal documents for bilingual South Tyrol, and, in this context, on the creation, upgrading, and maintenance of terminological resources.