Improving Controllability of Educational Question Generation by Keyword Provision
This work addresses the need for more controllable and diverse question generation in educational reading practice and assessments, representing an incremental improvement.
The paper tackled the problem of low controllability and question difficulty in educational question generation by advancing a state-of-the-art model from 11.96 to 20.19 BLEU 4 score and proposing a keyword provision method to guide question generation, demonstrating feasibility for improving diversity and controllability.
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.