Can Esculape cure the complex of œdipe in the medical domain?

Authors:
Mehdi Embarek;Olivier Ferret
Affiliations:
CEA LIST, Vision and Content Engineering Laboratory, France;CEA LIST, Vision and Content Engineering Laboratory, France
Venue:
RIAO '10 Adaptivity, Personalization and Fusion of Heterogeneous Information
Year:
2010

Citing 6
Cited 0

Towards terascale knowledge acquisition

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Question Answering in Restricted Domains: An Overview

Computational Linguistics
Answering Clinical Questions with Knowledge-Based and Statistical Techniques

Computational Linguistics
A knowledge based method for the medical question answering problem

Computers in Biology and Medicine
Biomedical question answering: A survey

Computer Methods and Programs in Biomedicine
Finding answers in the Œdipe system by extracting and applying linguistic patterns

CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article, we present Esculape, a question-answering system for French dedicated to family doctors and built from œdipe, an open-domain system. Esculape adds to œdipe the capability to exploit the concepts and relations of a domain model, the medical domain in the present case. Although a large number of resources exist in this domain (UMLS, MeSH ...), it is not possible to rely only on them, and more specifically on the relations they contain, to answer questions. We show how this difficulty can be overcome by learning linguistic patterns for identifying relations and applying them to extract answers.