Linguistically motivated knowledge management: exploitation of language resources for NLP applications

In this paper we describe how to exploit tailor-made Linguistic Resources (LR) accurately in order to hold up a Knowledge Management System (KMS) with the purpose of implementing human interaction with technologies and of meeting specific knowledge needs. LR developed in this way can be used in Natural Language Processing (NLP) applications, such as: Information Retrieval (IR), Information Extraction (IE), Information Storage, Machine Translation (MT), ontology development, lexicon-dependent Semantic Web, query-free procedures for knowledge structuring, question answering. We also present a methodology for Multiword Unit (MWU) treatment. As a sample, we built a monitor corpus annotated for MWUs using XML and processed it with a Text Classification tool.