Sélection de réponses à des questions dans un corpus Web par validation

Question answering systems look for the answer of a question given in natural language in a large collection of documents. Web documents have a structure and a style different from those of newspaper articles. We developed a QA system based on an answer validation process able to handle Web specificity. Large number of candidate answers are extracted from short passages in order to be validated according to question and passage characteristics. The validation module is based on a machine learning approach. We show that our system outperforms a baseline by up to 48% in MRR (Mean Reciprocal Rank).