Del texto a la información

Abstract

In the last years, software applications centered on Natural Language Processing (NLP) have experimented a great significance, especially access to neither unrestricted, nor codified, textual information. In this context, information extraction systems from unrestricted texts, have been acquired a growing interest. Our proposal is twofold: on one side we present an information extraction environment, i.e. a specific NLP application. On the other side we describe how different modules, dealing different issues on Spanish NLP (lexical and morphological analysis, shallow syntactic analysis, learning text extraction rules, information extraction, etc.), are integrated in it, and how these modules could be used in new applications.

Postprint (published version)