Neural Question Generation from Text: A Preliminary Study
Qingyu Zhou† Nan Yang‡ Furu Wei‡ Chuanqi Tan♯ Hangbo Bao† Ming Zhou‡ †Harbin Institute of Technology, Harbin, China ‡Microsoft Research, Beijing, China ♯Beihang University, Beijing, China {nanya, fuwei, Contribution during internship at Microsoft Research.
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.
中文速览
如何让机器自动从一段文字里生成有意义的问题？过去的做法依赖人工设计的规则把句子转换成问题，灵活性差、难以迁移。这项工作提出了一个神经问题生成（Neural Question Generation, NQG）框架，用编码器-解码器（encoder-decoder）结构来完成这件事：编码器在读入句子的同时，还接收答案位置标记（BIO标注）以及词性、命名实体等词法特征，让模型知道"要围绕哪个答案来出题"；解码器则通过注意力机制和复制机制，逐词生成自然语言问题。在包含逾10万条问答对的SQuAD数据集上进行实验，NQG在BLEU-4自动评分和人工评分两项指标上均大幅领先基于规则的基线方法，生成的问题更流畅、更贴合答案。这项工作验证了用神经网络端到端生成问题的可行性，为自动构建大规模问答语料、辅助问答系统训练提供了新的思路。
原文 arXiv:1704.01792;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1704.01792v3