Learning to Ask: Neural Question Generation for Reading Comprehension

2017/04/29 by Xinya Du, Junru Shao, Du, Xinya +3 · 1 voice · 112 citations
Computer Science · #Artificial intelligence #Ask price #Comprehension #Computer science #Contrast (vision) #Encoding (memory) #Fluency #Grammar #Grammaticality #Linguistics #Natural Language Processing Techniques #Natural language processing #Paragraph #Parsing #Pipeline (software) #Reading (process) #Reading comprehension #Sentence #Sequence (biology) #Task (project management) #Text Readability and Simplification #Topic Modeling #cs.AI #cs.CL

paper · pdf · doi:10.48550/arxiv.1705.00106

published in arXiv (Cornell University) (Cornell University) · Accepted to ACL 2017, 11 pages

arxiv created 2017/04/29 · openalex publication_date 2017/04/29 · arxiv updated 2017/05/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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
• Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
• Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation
• Inquisitive Question Generation for High Level Text Comprehension
• Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
• Quiz-Style Question Generation for News Stories
• The RLLChatbot: a solution to the ConvAI challenge
• ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
• Natural Language Generation with Neural Variational Models
• GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
• Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text
• Multi-Hop Question Generation via Dual-Perspective Keyword Guidance
• HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Question Generation from SQL Queries Improves Neural Semantic Parsing
• An overview of artificial intelligence in computer-assisted language learning
• A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation
• Semantic Graphs for Generating Deep Questions
• BrickSmart: Leveraging Generative AI to Support Children's Spatial Language Learning in Family Block Play
• From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM

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