Neural Question Generation from Text: A Preliminary Study
This work addresses the need for more flexible and meaningful question generation in natural language processing, though it is incremental as it builds on existing neural models.
The authors tackled the problem of automatic question generation from text passages by proposing a neural encoder-decoder model that incorporates answer positions to produce answer-aware questions. Their preliminary study on the SQuAD dataset demonstrated that the method generates fluent and diverse questions.
Automatic question generation aims to generate questions from a text passage where the generated questions can be answered by certain sub-spans of the given passage. Traditional methods mainly use rigid heuristic rules to transform a sentence into related questions. In this work, we propose to apply the neural encoder-decoder model to generate meaningful and diverse questions from natural language sentences. The encoder reads the input text and the answer position, to produce an answer-aware input representation, which is fed to the decoder to generate an answer focused question. We conduct a preliminary study on neural question generation from text with the SQuAD dataset, and the experiment results show that our method can produce fluent and diverse questions.