Recent Advances in Neural Question Generation

2019/05/22 by Liangming Pan, Wenqiang Lei, Pan, Liangming +5 · 5 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.1905.08949

Abstract

Emerging research in Neural Question Generation (NQG) has started to integrate a larger variety of inputs, and generating questions requiring higher levels of cognition. These trends point to NQG as a bellwether for NLP, about how human intelligence embodies the skills of curiosity and integration. We present a comprehensive survey of neural question generation, examining the corpora, methodologies, and evaluation methods. From this, we elaborate on what we see as emerging on NQG's trend: in terms of the learning paradigms, input modalities, and cognitive levels considered by NQG. We end by pointing out the potential directions ahead.

Citations

• ImageNet classification with deep convolutional neural networks

Cited by

• VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation
• Towards Standard Criteria for human evaluation of Chatbots: A Survey
• Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• Semantic Bridge: Universal Multi-Hop Question Generation via AMR-Driven Graph Synthesis

Related

• A Survey on Neural Question Generation: Methods, Applications, and Prospects
• Modeling question asking using neural program generation
• Improving Neural Question Generation using World Knowledge
• Learning to Ask: Neural Question Generation for Reading Comprehension
• MixQG: Neural Question Generation with Mixed Answer Types