PhD. Thesis : Data Integration in a Question-Answering System on the

Feb 15, 2007 - In front of the following jury: - Guy LAPALME. Professor of the University of Montréal – RALI (Reviewer). - Pierre ZWEIGENBAUM. Research ...
13KB taille 37 téléchargements 217 vues
PhD. Thesis : Data Integration in a Question-Answering System on the Web Véronique Moriceau Defended on February, 15th 2007, In front of the following jury: - Guy LAPALME

Professor of the University of Montréal – RALI (Reviewer)

- Pierre ZWEIGENBAUM

Research Director of the CNRS – LIMSI (Reviewer)

- Régine ANDRÉ –OBRECHT

Professor of the University Toulouse III - IRIT (Examiner)

- Christian RETORÉ

Professor of the University Bordeaux I – LaBRI (Examiner)

- Patrick SÉGUÉLA

Synapse Développement

- Patrick SAINT-DIZIER

Research Director of the CNRS – IRIT (Supervisor)

Abstract:

In the framework of question-answering systems on the Web, our main goals are to model, develop and evaluate a system which can, from a question in natural language, search for relevant answers on the Web and generate a synthetic answer, even if the search engine selected several candidate answers. We focused on temporal and numerical questions. Our system deals with: - the integration of data from candidate answers by using a knowledge base and knowledge extracted from the Web. This component allows the detection of data inconsistencies and deals with user expectations in order to produce a relevant answer, - the generation of synthetic answers in natural language which are relevant w.r.t users. Indeed, generated answers have to be short, understandable and have to express the cooperative knowhow which has been used to solve data inconsistencies. We also propose evaluation methods to evaluate our system from a technical and cognitive point of view.

Keywords: question-answering system, data integration, génération de langue