terminology as knowledge in answer extraction

• DOI: 10.5167/uzh-19092
• Publication Date: 2002-01-01
• Authors: Rinaldi, Fabio; Dowdall, J; Hess, M; Kaljurand, K; Koitand, M; Kahusk, N; Vider, K
• Keywords: 10105 Institute of Computational Linguistics; 410 Linguistics; 000 Computer science, knowledge & systems

It is well known that one of the greatest hurdles in automatically processing technical documentation is the large amount of specific terminology that characterizes these domains. Terminology poses two major challenges to the developers of NLP applications: how to identify domain specific terms in the documents and how to efficiently process them. In this paper we will present methodologies that we have used to extract and bootstrap a terminological database and its usage in an answer extraction system.