Textual entailment recognition based on dependency analisys and WordNet

The UNED-NLP Group Recognizing Textual Entailment System is based on the use of a broad-coverage parser to extract dependency relations and a module which obtains lexical entailment relations from WordNet. The work aims at comparing whether the matching of dependency trees subestructures give better...

Descripción completa

Detalles Bibliográficos
Autores: Herrera de la Cruz, Jesús, Peñas, Anselmo, Verdejo, Felisa
Tipo de recurso: artículo
Fecha de publicación:2005
País:España
Institución:Universidad Complutense de Madrid (UCM)
Repositorio:Docta Complutense
Idioma:español
OAI Identifier:oai:docta.ucm.es:20.500.14352/50113
Acceso en línea:https://hdl.handle.net/20.500.14352/50113
Access Level:acceso abierto
Palabra clave:Reconocimiento de implicación textual
Análisis de dependencias
Árbol de dependencias
WordNet
Textual entailment recognition
Dependency analisys
Dependency tree
Inteligencia artificial (Informática)
Lingüística
1203.04 Inteligencia Artificial
57 Lingüística
Descripción
Sumario:The UNED-NLP Group Recognizing Textual Entailment System is based on the use of a broad-coverage parser to extract dependency relations and a module which obtains lexical entailment relations from WordNet. The work aims at comparing whether the matching of dependency trees subestructures give better evidence of entailment than the matching of plain text alone.