UNED at PASCAL RTE-2 challenge
This paper reports the description of the developed system and the results obtained in the participation of the UNED in the Second Recognizing Textual Entailment (RTE) Challenge. New techniques and tools have been added: enriched queries to WordNet, detection of numeric expressions and their entailm...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | capítulo de libro |
| Fecha de publicación: | 2006 |
| País: | España |
| Institución: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | español |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/53615 |
| Acceso en línea: | https://hdl.handle.net/20.500.14352/53615 |
| Access Level: | acceso abierto |
| Palabra clave: | reconocimiento de implicación textual análisis de dependencias detección de expresiones numéricas recognising textual entailment dependency analysis recognising numeric expressions Inteligencia artificial (Informática) Lingüística 1203.04 Inteligencia Artificial 57 Lingüística |
| Sumario: | This paper reports the description of the developed system and the results obtained in the participation of the UNED in the Second Recognizing Textual Entailment (RTE) Challenge. New techniques and tools have been added: enriched queries to WordNet, detection of numeric expressions and their entailment, and Support Vector Machine classi cation (SVM) are the more relevant. The accuracy performed is slightly higher than the one from the previous edition system. |
|---|