Consultas Degradadas en Recuperación de Información Textual
- Otero Pombo, Juan
- Vilares, Jesús
- Vilares Ferro, Manuel
ISSN: 1135-5948
Argitalpen urtea: 2009
Zenbakia: 42
Orrialdeak: 9-16
Mota: Artikulua
Beste argitalpen batzuk: Procesamiento del lenguaje natural
Laburpena
In this paper, we propose two different alternatives to deal with degraded queries on Spanish Information Retrieval applications. The first is based on character n-grams, and has no dependence on the linguistic knowledge and resources available. In the second, we propose two spelling correction techniques, one of which has a strong dependence on a stochastic model that must be previously built from a PoStagged corpus. In order to study their validity, a testing framework has been designed and applied on both approaches for evaluation.