A Survey on Neural Question Generation: Methods, Applications, and Prospects

arXiv:2402.18267v1 Announce Type: new
Abstract: In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG's background, encompassing the task's problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, …

abstract applications arxiv cs.ai cs.cl diverse generate images inputs knowledge network neural network overview prospects question questions survey type