In this paper we describe our strategy in the course of our participation in the 2012 QA4MRE main task. We follow a lexical approach, based on both Word Proximity and similarity measures. In the former, we implement a method that was successfully applied in the " Who Wants to be a Millionaire " contest; in the later we use the notion of " extent " , that… (More)
We introduce QGASP, a system that performs question generation by using lexical, syntactic and semantic information. QGASP uses this information both to learn patterns and to generate questions. In this paper, we briefly describe its architecture.