Neural Question Generation from Text: A Preliminary Study

TL;DR

This paper explores using neural encoder-decoder models for automatic question generation from text, demonstrating the ability to produce fluent, diverse, answer-aware questions in a preliminary study.

Contribution

It introduces a neural question generation approach that leverages answer position information to produce more relevant questions from natural language sentences.

Findings

The method generates fluent, diverse questions.

Preliminary results on SQuAD show promising performance.

Neural models outperform traditional heuristic methods.

Abstract

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.