arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.18267cs.CLcs.AI
收藏

神经问题生成综述:方法、应用与展望

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

Renmin University of China(中国人民大学);Singapore Management University(新加坡管理大学);National University of Singapore(新加坡国立大学)

Shasha Guo, Lizi Liao, Cuiping Li, Tat-Seng Chua

AI总结:

本文综述神经问题生成(NQG),按结构化、非结构化与混合输入分类梳理模型、应用、评估及挑战,并展望趋势、提供论文数据集与代码资源。

摘要:

在本综述中,我们详细考察了神经问题生成(Neural Question Generation,NQG)的进展,该领域利用神经网络技术,从知识库、文本和图像等多种输入中生成相关问题。本综述首先概述 NQG 的背景,包括该任务的问题形式化、常用基准数据集、既定评估指标以及显著应用。随后,综述系统地将 NQG 方法划分为三个主要类别:结构化 NQG,利用有组织的数据源;非结构化 NQG,聚焦文本或视觉内容等结构较松散的输入;以及混合 NQG,借助多种输入模态。在此分类之后,本文深入分析了为每一类定制的不同神经网络模型,讨论其内在优势和潜在局限。综述最后对 NQG 的发展轨迹提出前瞻性视角,识别新兴研究趋势和未来发展路径。伴随本综述的还有经过整理的相关研究论文、数据集和代码集合,并在 GitHub 上系统组织,为深入研究 NQG 的人员提供广泛参考。

英文摘要:

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, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed by an in-depth analysis of the distinct neural network models tailored for each category, discussing their inherent strengths and potential limitations. The survey culminates with a forward-looking perspective on the trajectory of NQG, identifying emergent research trends and prospective developmental paths. Accompanying this survey is a curated collection of related research papers, datasets and codes, systematically organized on Github, providing an extensive reference for those delving into NQG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑