Neural Question Generation from Text: A Preliminary Study

Abstract

Automatic question generation aims to generate questions from a text passage where the generated questions can be answered by certain sub-spans of the given passage. Traditional methods mainly use rigid heuristic rules to transform a sentence into related questions. In this work, we propose to apply the neural encoder-decoder model to generate meaningful and diverse questions from natural language sentences. The encoder reads the input text and the answer position, to produce an answer-aware input representation, which is fed to the decoder to generate an answer focused question. We conduct a preliminary study on neural question generation from text with the SQuAD dataset, and the experiment results show that our method can produce fluent and diverse questions.

Submitted to EMNLP 2017

References in corpus (2)

• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Machine Comprehension Using Match-LSTM and Answer Pointer

Cited by in corpus (14)

• Question Answering and Question Generation as Dual Tasks
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• Learning to Generate Questions by Learning What not to Generate
• A Unified Query-based Generative Model for Question Generation and Question Answering
• Improving Neural Question Generation using Answer Separation
• Improving Non-autoregressive Generation with Mixup Training
• Zero-shot Fact Verification by Claim Generation
• Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders
• Sequential Copying Networks
• ColdGANs: Taming Language GANs with Cautious Sampling Strategies
• Learning to Ask Screening Questions for Job Postings
• Semantic Graphs for Generating Deep Questions
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Learning to Generate Questions with Adaptive Copying Neural Networks