Question generation for language café interaction between robot and human : NLP applied in a robot

Sammanfattning: Conversational robots can be used in several contexts, one of them being language cafés. This setting demands that the robot in question can converse on many different subjects and move between them smoothly. For this to be possible one needs to generate many questions on a range of subjects and find a way of moving from one subject to another. This work aims to do this by generating questions using a template framework and navigating between them using clustering, a scalable solution which is adapted to language café settings. The general value of language cafés and their role in a language learning process is also discussed.