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.

Les systèmes de Questions Réponse ont besoin de connaissances sémantiques pour trouver dans les documents des termes susceptibles d’être des reformulations des termes de la question. Cependant, l’utilisation de ressources sémantiques peut apporter un bruit important et altérer la précision du système. ne fournit qu’une partie des reformulations possibles. Cet article présente un cadre d’évaluation pour les ressources sémantiques dans les systèmes de question-réponse. Il décrit la fabrication semi-automatique d’un corpus de questions et de réponses destiné à étudier les reformulations présentes entre termes de la question et termes de la réponse. Il étudie la fréquence et la fiabilité des reformulations extraites de l’ontologie WordNet.