Learning to Ask: Neural Question Generation for Reading Comprehension

2017/04/29 by Xinya Du, Junru Shao, Du, Xinya +3 · 1 voice · 8 citations
Computer Science · #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.1705.00106

openalex publication_date 2017/04/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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).

Citations

• Microsoft COCO Captions: Data Collection and Evaluation Server

Cited by

• Backprompting: Leveraging Synthetic Production Data for Health Advice Guardrails
• The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation
• Subjective Question Generation and Answer Evaluation using NLP
• Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization
• Ask Good Questions for Large Language Models
• Unsupervised Question Answering for Fact-Checking
• Learning Facts at Scale with Active Reading
• Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis

Discussions

• Learning to Ask: Neural Question Generation [hn, 23 points, 1 comments]

Related

• Automating Reading Comprehension by Generating Question and Answer Pairs
• Machine Comprehension by Text-to-Text Neural Question Generation
• Neural Question Generation from Text: A Preliminary Study
• Recent Advances in Neural Question Generation
• Neural Models for Key Phrase Detection and Question Generation