A corpus-based bootstrapping algorithm for Semi-Automated semantic lexicon construction
Natural Language Engineering
Automatic acquisition of hyponyms from large text corpora
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Finding parts in very large corpora
ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics
Automatic Discovery of Part-Whole Relations
Computational Linguistics
Hi-index | 0.00 |
In this paper we propose a method to exploit analytical definitions extracted from Spanish corpora, in order to build a lexical network based on the hyponymy/hyperonymy, part/whole and attribution relations. Our method considers the following steps: (a) the recognition and extraction of definitional contexts from specialized documents, (b) the identification of analytical definitions on these definitional contexts, using verbal predications, (c) the syntactic and probabilistic analysis of the association observed between verbal predication and analytical definitions, (d) the identification of the hyponymy/hyperonymy, part/whole and attribution relations based on the lexical information that lies between predications and definitions and other types of phrases, in particular prepositional phrases mapped by the preposition de (Eng. of/from).