Reinforced Dynamic Reasoning for Conversational Question Generation
Reinforced Dynamic Reasoning for Conversational Question Generation
复制标题
DOI：
10.18653/v1/p19-1203
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Boyuan Pan;Hao Li;Ziyu Yao;Deng Cai;Huan Sun
中科院分区：
文献类型：
--
作者：
Boyuan Pan;Hao Li;Ziyu Yao;Deng Cai;Huan Sun
本文研究了一种新的会话问题生成（CQG）任务，该任务是基于一篇文章和一段对话历史（即以前的问答对）生成一个问题。CQG是开发智能代理的关键任务，它可以驱动问答式对话或测试用户对给定段落的理解。为此，我们提出了一种名为增强动态推理网络的新方法，该方法基于一般编码器-解码器框架，但以动态方式结合推理过程，以更好地理解关于进入一般编码器-解码器框架的通道的问题以及下一步要问的问题。为了鼓励产生有意义的问题，我们利用一个流行的问答（QA）模型来提供反馈，并使用强化学习机制对问题生成器进行微调。最近发布的CoQA数据集的实证结果表明，与各种基线和模型变量相比，我们的方法是有效的。此外，为了展示我们方法的适用性，我们还将其应用于SQuAD中段落的多回合问答对话。
This paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i.e., previous turns of question-answer pairs). CQG is a crucial task for developing intelligent agents that can drive question-answering style conversations or test user understanding of a given passage. Towards that end, we propose a new approach named Reinforced Dynamic Reasoning network, which is based on the general encoder-decoder framework but incorporates a reasoning procedure in a dynamic manner to better understand what has been asked and what to ask next about the passage into the general encoder-decoder framework. To encourage producing meaningful questions, we leverage a popular question answering (QA) model to provide feedback and fine-tune the question generator using a reinforcement learning mechanism. Empirical results on the recently released CoQA dataset demonstrate the effectiveness of our method in comparison with various baselines and model variants. Moreover, to show the applicability of our method, we also apply it to create multi-turn question-answering conversations for passages in SQuAD.