Recent Advances in Neural Question Generation
This is an incremental survey paper that synthesizes existing research for the NLP community.
The paper provides a comprehensive survey of neural question generation, examining trends in corpora, methodologies, and evaluation methods, and elaborates on emerging directions in learning paradigms, input modalities, and cognitive levels.
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.