Learning to Ask: Neural Question Generation for Reading Comprehension

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).

Accepted to ACL 2017, 11 pages

References in corpus (2)

• Sequence to Sequence Learning with Neural Networks
• Microsoft COCO Captions: Data Collection and Evaluation Server

Cited by in corpus (39)

• Evaluation of Text Generation: A Survey
• Unsupervised Question Answering by Cloze Translation
• Biomedical Question Answering: A Survey of Approaches and Challenges
• Learning to Generate Questions by Learning What not to Generate
• ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training
• A Joint Model for Question Answering and Question Generation
• Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds
• A Unified Query-based Generative Model for Question Generation and Question Answering
• Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
• Natural Question Generation with Reinforcement Learning Based Graph-to-Sequence Model
• Putting the Horse Before the Cart:A Generator-Evaluator Framework for Question Generation from Text
• Automating Reading Comprehension by Generating Question and Answer Pairs
• Natural Language Generation with Neural Variational Models
• Information Maximizing Visual Question Generation
• Improving Neural Question Generation using Answer Separation
• Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
• ColdGANs: Taming Language GANs with Cautious Sampling Strategies
• Question Generation by Transformers
• Identifying Well-formed Natural Language Questions
• Multimodal Differential Network for Visual Question Generation
• Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
• Towards a Better Metric for Evaluating Question Generation Systems
• Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
• Semantic Graphs for Generating Deep Questions
• Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation
• Question Generation from SQL Queries Improves Neural Semantic Parsing
• Evaluating Text-to-Image Matching using Binary Image Selection (BISON)
• Unsupervised Question Answering for Fact-Checking
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Deep Exemplar Networks for VQA and VQG
• Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
• Engaging Audiences in Virtual Museums by Interactively Prompting Guiding Questions
• Inquisitive Question Generation for High Level Text Comprehension
• Learning to Generate Questions with Adaptive Copying Neural Networks
• The RLLChatbot: a solution to the ConvAI challenge
• AGenT Zero: Zero-shot Automatic Multiple-Choice Question Generation for Skill Assessments
• Quiz-Style Question Generation for News Stories
• A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation
• Can questions summarize a corpus? Using question generation for characterizing COVID-19 research