CONSISTENT: Open-Ended Question Generation From News Articles
This addresses the challenge of creating non-factoid questions for news media, though it appears incremental.
The authors tackled generating open-ended questions from news articles, proposing CONSISTENT, which outperformed baselines in evaluations.
Recent work on question generation has largely focused on factoid questions such as who, what, where, when about basic facts. Generating open-ended why, how, what, etc. questions that require long-form answers have proven more difficult. To facilitate the generation of open-ended questions, we propose CONSISTENT, a new end-to-end system for generating open-ended questions that are answerable from and faithful to the input text. Using news articles as a trustworthy foundation for experimentation, we demonstrate our model's strength over several baselines using both automatic and human=based evaluations. We contribute an evaluation dataset of expert-generated open-ended questions.We discuss potential downstream applications for news media organizations.