This paper presents a Named Entities (NE) recognition system for the English written language, which combines the wealth of the WordNet taxonomy and the effectiveness of traditional rule-based approaches. The core of the system relies on the combination of approximately 200 language-dependent rules with a set of predicates, defined on the WordNet hierarchy, for the identification of both proper nouns and trigger words. The strengths of this approach are twofold. First, the use of a semantic network allows it to cope with the difficulty of building and maintaining extensive gazetteers. Second, considering the recent spread of WordNet-like semantic networks for languages other than English and aligned with the English version, the use of language-independent predicates offers a useful basis for achieving multilinguality.
Description
A WordNet-based approach to Named Entities recognition
%0 Conference Paper
%1 magnini02ner
%A Magnini, Bernardo
%A Negri, Matteo
%A Prevete, Roberto
%A Tanev, Hristo
%B COLING-02 on SEMANET
%C Morristown, NJ, USA
%D 2002
%I Association for Computational Linguistics
%K 2002 COLING-02 named-entity ner nlp recognition text-mining wordnet
%P 1--7
%R http://dx.doi.org/10.3115/1118735.1118744
%T A WordNet-based approach to Named Entities recognition
%U http://portal.acm.org/citation.cfm?id=1118744
%X This paper presents a Named Entities (NE) recognition system for the English written language, which combines the wealth of the WordNet taxonomy and the effectiveness of traditional rule-based approaches. The core of the system relies on the combination of approximately 200 language-dependent rules with a set of predicates, defined on the WordNet hierarchy, for the identification of both proper nouns and trigger words. The strengths of this approach are twofold. First, the use of a semantic network allows it to cope with the difficulty of building and maintaining extensive gazetteers. Second, considering the recent spread of WordNet-like semantic networks for languages other than English and aligned with the English version, the use of language-independent predicates offers a useful basis for achieving multilinguality.
@inproceedings{magnini02ner,
abstract = {This paper presents a Named Entities (NE) recognition system for the English written language, which combines the wealth of the WordNet taxonomy and the effectiveness of traditional rule-based approaches. The core of the system relies on the combination of approximately 200 language-dependent rules with a set of predicates, defined on the WordNet hierarchy, for the identification of both proper nouns and trigger words. The strengths of this approach are twofold. First, the use of a semantic network allows it to cope with the difficulty of building and maintaining extensive gazetteers. Second, considering the recent spread of WordNet-like semantic networks for languages other than English and aligned with the English version, the use of language-independent predicates offers a useful basis for achieving multilinguality.},
added-at = {2007-07-23T13:24:51.000+0200},
address = {Morristown, NJ, USA},
author = {Magnini, Bernardo and Negri, Matteo and Prevete, Roberto and Tanev, Hristo},
biburl = {https://www.bibsonomy.org/bibtex/2fd67c961069a5850b6a1726e003c023e/zeno},
booktitle = {COLING-02 on SEMANET},
description = {A WordNet-based approach to Named Entities recognition},
doi = {http://dx.doi.org/10.3115/1118735.1118744},
ee = {http://portal.acm.org/citation.cfm?id=1118744},
interhash = {99fda915bf279f9506998746b91f1dd7},
intrahash = {fd67c961069a5850b6a1726e003c023e},
keywords = {2002 COLING-02 named-entity ner nlp recognition text-mining wordnet},
pages = {1--7},
publisher = {Association for Computational Linguistics},
timestamp = {2007-07-23T14:07:39.000+0200},
title = {A WordNet-based approach to Named Entities recognition},
url = {http://portal.acm.org/citation.cfm?id=1118744},
year = 2002
}