Ranking Automatically Generated Questions Using Common Human Queries
Yllias Chali, Sina Golestanirad · 2016
In this paper, we challenge a form of paragraph-to-question generation task.We propose a question generation system which can generate a set of comprehensive questions from a body of text.Besides the tree kernel functions to assess the grammatically of the generated questions, our goal is to rank them by using community-based question answering systems to calculate the importance of the generated questions.The main assumption behind our work is that each body of text is related to a topic of interest and it has a comprehensive information about the topic.