Question Generation (QG) receives increasing research attention in NLP community. One motivation for QG is that QG significantly facilitates the preparation of educational reading practice and assessments. While the significant advancement of QG techniques was reported, current QG results are not ideal for educational reading practice assessment in terms of \textit{controllability} and \textit{question difficulty}. This paper reports our results toward the two issues. First, we report a state-of-the-art exam-like QG model by advancing the current best model from 11.96 to 20.19 (in terms of BLEU 4 score). Second, we propose to investigate a variant of QG setting by allowing users to provide keywords for guiding QG direction. We also present a simple but effective model toward the QG controllability task. Experiments are also performed and the results demonstrate the feasibility and potentials of improving QG diversity and controllability by the proposed keyword provision QG model.

The government is using artificial intelligence in tasks ranging from planning space missions to forecasting job growth. Given the potential effects of these technologies on culture and economy, U.S. Chief Technology Officer Megan Smith says the government's larger challenge is to bring "humanity's greatest talent" to bear on the development and direction of AI. To hear more, watch her talk at the 2016 Global Entrepreneurship Summit partner event, "The Future of Artificial Intelligence."