@inproceedings{b4064f70aedb4854a6405e8c30954197,
title = "A domain-independent approach to IE rule development",
abstract = "A key element for the extraction of information in a natural language document is a set of shallow text analysis rules, which are typically based on pre-defined linguistic patterns. Current Information Extraction research aims at the automatic or semi-automatic acquisition of these rules. Within this research framework, we consider in this paper the potential for acquiring generic extraction patterns. Our research is based on the hypothesis that, terms (the linguistic representation of concepts in a specialised domain) and Named Entities (the names of persons, organisations and dates of importance in the text) can together be considered as the basic semantic entities of textual information and can therefore be used as a basis for the conceptual representation of domain specific texts and the definition of what constitutes an information extraction template in linguistic terms. The extraction patterns discovered by this approach involve significant associations of these semantic entities with verbs and they can subsequently be translated into the grammar formalism of choice.",
author = "Kalliopi Zervanou and John McNaught",
year = "2004",
language = "English",
series = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",
publisher = "European Language Resources Association (ELRA)",
pages = "745--748",
editor = "Xavier, {Maria Francisca} and Rute Costa and Fatima Ferreira and Lino, {Maria Teresa} and Raquel Silva",
booktitle = "Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004",
note = "4th International Conference on Language Resources and Evaluation, LREC 2004 ; Conference date: 26-05-2004 Through 28-05-2004",
}