Learning to Ask: Neural Question Generation for Reading Comprehension

TL;DR

This paper presents an end-to-end neural question generation model that outperforms rule-based systems in generating natural and challenging questions for reading comprehension tasks.

Contribution

It introduces a trainable sequence-to-sequence neural model that does not rely on hand-crafted rules or complex NLP pipelines for question generation.

Findings

Significantly outperforms state-of-the-art rule-based systems

Generated questions are rated more natural and challenging by humans

Encoding at paragraph level improves question quality

Abstract

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).