Affiliation:
1. Université du Québec à Trois-Rivières
2. Universidad de Granada
Abstract
Abstract
Hyponymy is an essential semantic relation in terminology, as it represents the hierarchical organization of concepts. Much has been written about hyponymy extraction. However, terminologists working with French do not currently have user-friendly and freely available tools to automatically extract hyper-hyponymic pairs from their own corpora. This paper presents the most recent version of the ESSG (EcoLexicon Semantic Sketch Grammar) methodology, a knowledge-pattern-based approach that enables Sketch Engine to extract semantic relations. This methodology is applied to the development and evaluation of the ESSG-fr, a semantic sketch grammar for hyponymy extraction in French. The evaluation results show that the ESSG-fr is a reliable domain-independent tool for terminologists wishing to extract simple hyper-hyponymic pairs and the corresponding concordances from specialized corpora.
Publisher
John Benjamins Publishing Company
Subject
Library and Information Sciences,Communication,Language and Linguistics
Reference61 articles.
1. Pattern-based approaches to semantic relation extraction: A state-of-the-art
2. Designing and evaluating patterns for relation acquisition from texts with Caméléon
3. Les relations sémantiques : du linguistique au formel;Aussenac-Gilles;Cahiers de grammaire,2000
4. TerminoWeb: A Software Environment for Term Study in Rich Contexts;Barrière,2006