Cross Lingual Question Answering using CINDI_QA for QA@CLEF 2007

This article presents the first participation of the CINDI group in the Multiple Language Question Answering Cross Language Evaluation Forum (QA@CLEF). We participated in a track using French as the source language and English as the target language. CINDI_QA first uses an online translation tool to convert the French input question into an English sentence. Second, a Natural Language Parser extracts keywords such as verbs, nouns, adjectives and capitalized entites from the query. Third, synonyms of those keywords are generated thanks to a Lexical Reference module. Fourth, our integrated Searching and Indexing component localises the answer candidates from the QA@CLEF data collection provided to us. Finally, the candidates are matched against our existing set of templates to decide on the best answer to return to the user. Two runs were submitted. Having missed using a large part of the corpora, CINDI_QA was only able to generate correct and exact answers for 13% of the questions it received.