Learning to Ask: Neural Question Generation for Reading Comprehension
This work addresses the problem of generating natural and challenging questions from text passages for reading comprehension tasks, representing a novel approach rather than an incremental improvement.
The authors tackled automatic question generation for reading comprehension by introducing an attention-based sequence learning model that is trainable end-to-end, eliminating the need for hand-crafted rules or NLP pipelines. Their system significantly outperformed the state-of-the-art rule-based system in automatic evaluations and was rated more natural and difficult to answer in human evaluations.
We study automatic question generation for sentences from text passages in reading comprehension. We introduce an attention-based sequence learning model for the task and investigate the effect of encoding sentence- vs. paragraph-level information. In contrast to all previous work, our model does not rely on hand-crafted rules or a sophisticated NLP pipeline; it is instead trainable end-to-end via sequence-to-sequence learning. Automatic evaluation results show that our system significantly outperforms the state-of-the-art rule-based system. In human evaluations, questions generated by our system are also rated as being more natural (i.e., grammaticality, fluency) and as more difficult to answer (in terms of syntactic and lexical divergence from the original text and reasoning needed to answer).