“…Using natural language in educational software allows students to spend their cognitive resources on the learning task, and also develop more socialbased agents [RODRÍGUEZ, S., et al 2011]. For this reason, this kind of agents have been employed to develop a number of educational systems in very different domains, including tutoring [PON-BARRY, H., et al 2006], conversation practice for language learners [FRYER, L., et al 2006], pedagogical agents and learning companions [CAVAZZA, M., et al 2010], dialogs to promote reflection and metacognitive skills [KERLY, A., et al 2008b], or role-playing actors in simulated experiential learning environments [GRIOL, D., et al 2012a], etc. To successfully manage the interaction with users, these agents are usually developed following a modular architecture, which generally includes the following tasks: automatic speech recognition (ASR), spoken language understanding (SLU), dialog management (DM), database management (DB), natural language generation (NLG), and text-to-speech synthesis (TTS).…”