The task of response selection in multi-turn dialogue is to find the best option from all candidates. In order to improve the reasoning ability of the model, previous studies pay more attention to using explicit algorithms to model the dependencies between utterances, which are deterministic, limited and inflexible. In addition, few studies consider differences between the options before and after reasoning. In this paper, we propose an Implicit Relational Reasoning Graph Network to address these issues, which consists of the Utterance Relational Reasoner (URR) and the Option Dual Comparator (ODC). URR aims to implicitly extract dependencies between utterances, as well as utterances and options, and make reasoning with relational graph convolutional networks. ODC focuses on perceiving the difference between the options through dual comparison, which can eliminate the interference of the noise options. Experimental results on two multi-turn dialogue reasoning benchmark datasets MuTual and MuTual+ show that our method significantly improves the baseline of four pretrained language models and achieves state-of-the-art performance. The model surpasses human performance for the first time on the MuTual dataset.

翻译：多轮对话中的响应选择任务旨在从所有候选中选出最佳选项。为提高模型推理能力，以往研究更注重使用显式算法建模话语间依赖关系，但此类方法具有确定性、局限性和僵化性。此外，鲜有研究考虑推理前后选项间的差异。针对上述问题，本文提出隐式关系推理图网络，该网络包含话语关系推理器与选项双重比较器。话语关系推理器旨在隐式提取话语间及话语与选项间的依赖关系，并通过关系图卷积网络进行推理；选项双重比较器则通过双重对比感知选项间的差异，从而消除噪声选项的干扰。在两个多轮对话推理基准数据集MuTual和MuTual+上的实验结果表明，本方法显著提升了四种预训练语言模型的基线性能，并达到当前最优水平。该模型首次在MuTual数据集上超越了人类表现。