Neural Question Generation from Text: A Preliminary Study

TL;DR

This work tackles automatic question generation from text using a neural encoder-decoder (NQG) framework. It enhances the encoder with an answer-position indicator and lexical features (POS, NER) and uses an attention-based decoder with a copy mechanism to produce answer-focused questions. Evaluations on SQuAD show improvements over baselines in BLEU-4 and human judgments, with ablations confirming the importance of answer-position signals and lexical cues. The results demonstrate the feasibility of data-driven QG for educational and QA corpus generation, suggesting future QA integration and domain expansion.

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.

Figures (2)

• Figure 1: Overview of the Neural Question Generation (NQG) framework.
• Figure 2: Precision and recall of question types.