Semantic knowledge in Question-Answering systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

Semantic knowledge in Question-Answering systems

Résumé

QA systems need semantic knowledge to find in documents variations of the question terms. They benefit from the use of knowledge resources such as synonym dictionaries or ontologies like WordNet. Our goal here is to study to which extent variations are needed and to determine what kinds of variations are useful or necessary for these systems. This study is based on different corpora in which we analyze semantic term variations, based on reference sets of possible variations.
Fichier principal
Vignette du fichier
kraq05.pdf (49.89 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02327365 , version 1 (22-10-2019)

Identifiants

  • HAL Id : hal-02327365 , version 1

Citer

Vincent Barbier, Brigitte Grau, Anne-Laure Ligozat, Isabelle Robba, Anne Vilnat. Semantic knowledge in Question-Answering systems. IJCAI Workshop on Knowledge and Reasoning for Answering Questions (KRAQ), Aug 2005, EDINBURGH - SCOTLAND, Unknown Region. ⟨hal-02327365⟩
29 Consultations
9 Téléchargements

Partager

Gmail Facebook X LinkedIn More