Les systèmes de questions réponses recherchent la réponse à une question posée en langue naturelle dans un ensemble de documents. Les collectionsWeb diffèrent des articles de journaux de par leurs structures et leur style. Pour tenir compte de ces spécificités nous avons développé un système fondé sur une approche robuste de validation où des réponses candidates sont extraites à partir de courts passages textuels puis ordonnées par apprentissage. Les résultats montrent une amélioration du MRR (Mean Reciprocal Rank) de 48% par rapport à la baseline.

Question answering (QA) systems aim at retrieving precise information from a large collection of documents. To be considered as reliable by users, a QA system must provide elements to evaluate the answer. This notion of answer justification can also be useful when developping a QA system in order to give criteria for selecting correct answers. An answer justification can be found in a sentence, a passage made of several consecutive sentences or several passages of a document or several documents. Thus, we are interesting in pinpointing the set of information that allows to verify the correctness of the answer in a candidate passage and the question elements that are missing in this passage. Moreover, the relevant information is often given in texts in a different form from the question form: anaphora, paraphrases, synonyms. In order to have a better idea of the importance of all the phenomena we underlined, and to provide enough examples at the QA developer's disposal to study them, we decided to build an annotated corpus.