Recent Advances in Neural Question Generation

TL;DR

This paper surveys recent progress in neural question generation, highlighting new input types, cognitive levels, and evaluation methods, and discusses future research directions in this evolving NLP field.

Contribution

It provides a comprehensive overview of neural question generation, analyzing datasets, methods, and evaluation, and identifies emerging trends and future directions.

Findings

NQG incorporates diverse input modalities and higher cognitive levels.

Survey highlights evolving methodologies and evaluation techniques.

Identifies future research directions in NQG.

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.