Publicación: Método para la construcción automática de ontologías lingüísticas ligeras basadas en corpus temáticos.
Fecha
2022-09-01
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Escuela Técnica Superior de Ingeniería Informática. Departamento de Inteligencia Artificial
Resumen
En el trabajo que se presenta se pretende, como objetivo principal, el desarrollo, y posterior síntesis, de un método propuesto por el ponente que, a partir de un corpus temático bien escogido, una ontología lingüística general y otros recursos permita elaborar, para una determinada temática, unas ontologías lingüísticas ligeras representativas de dicha temática particularizando la Ontología Lingüística General. En pos de dicho objetivo se alcanzaron hitos constitutivos parciales como la extracción de los términos del corpus con una determinada estructura y su posterior paso a conceptos con otra determinada estructura; para ello se precisó de la ayuda de dicha ontología lingüística general así como del paradigma de las Reglas de Asociación. La elección de una y otra estructura fue encaminada a facilitar la selección adecuada de los conceptos mas representativos, asi como la desambiguación de la polisemia. Cada una de estas ontologías lingüísticas ligeras representa una relación. En particular, en este trabajo se sintetizaron relaciones de sinonimia, de hiperonimia y de coocurrencia.
The main objective of the academic work presented here is the development, and subsequent synthesis, of a method proposed by the author that, from a well-chosen thematic corpus, a general linguistic ontology and other resources allows to elaborate, for a certain theme, some light linguistic ontologies representative of said theme, particularizing the General Linguistic Ontology. In pursuit of this objective, partial constitutive milestones were reached, such as the extraction of the terms from the corpus with a certain structure and their subsequent transition to concepts with another certain structure; For this, the help of said general linguistic ontology was needed, as well as the paradigm of the Rules of Association. The choice of one or the other structure was aimed at facilitating the adequate selection of the most representative concepts, as well as the disambiguation of polysemy. Each of these lightweight linguistic ontologies represents a relation. In particular, in this academic work synonymy, hyperonymy and co-occurrence relations were synthesized.
The main objective of the academic work presented here is the development, and subsequent synthesis, of a method proposed by the author that, from a well-chosen thematic corpus, a general linguistic ontology and other resources allows to elaborate, for a certain theme, some light linguistic ontologies representative of said theme, particularizing the General Linguistic Ontology. In pursuit of this objective, partial constitutive milestones were reached, such as the extraction of the terms from the corpus with a certain structure and their subsequent transition to concepts with another certain structure; For this, the help of said general linguistic ontology was needed, as well as the paradigm of the Rules of Association. The choice of one or the other structure was aimed at facilitating the adequate selection of the most representative concepts, as well as the disambiguation of polysemy. Each of these lightweight linguistic ontologies represents a relation. In particular, in this academic work synonymy, hyperonymy and co-occurrence relations were synthesized.
Descripción
Categorías UNESCO
Palabras clave
ontología lingüística, conceptos, términos, minería de textos, Ley de Zipf, polisemia, linguistic ontology, concepts, terms, text mining, Zipf's Law, polysemy
Citación
Centro
Facultades y escuelas::E.T.S. de Ingeniería Informática
Departamento
Inteligencia Artificial