基于对话结构的多轮对话生成模型

目前，多轮对话生成研究大多使用基于RNN或Transformer的编码器-解码器架构.但这些序列模型都未能很好地考虑到对话结构对于下一轮对话生成的影响.针对此问题，在传统的编码器-解码器模型的基础上，使用图神经网络结构对对话结构信息进行建模，从而有效地刻画对话的上下文中的关联逻辑.针对对话设计了基于文本相似度的关联结构、基于话轮转换的关联结构和基于说话人的关联结构，利用图神经网络进行建模，从而实现对话上下文内的信息传递及迭代.基于DailyDialog数据集的实验结果表明，与其他基线模型相比，该模型在多个指标上有一定的提升.这说明使用图神经网络建立的模型能够有效地刻画对话中的多种关联结构，从而有利于神经网络生成高质量的对话回复.

Multi-turn Dialogue Generation Model with Dialogue Structure

Recent research on multi-turn dialogue generation has focused on RNN or Transformer-based encoder-decoder architecture. However, most of these models ignore the influence of dialogue structure on dialogue generation. To solve this problem, this study proposes to use graph neural network structure to model the dialogue structure information, thus effectively describing the complex logic within a dialogue. Text-based similarity relation structure, turn-switching-based relation structure, and speaker-based relation structure are proposed for dialogue generation, and graph neural network is employed to realize information transmission and iteration in dialogue context. Extensive experiments on the DailyDialog dataset show that the proposed model consistently outperforms other baseline models in many indexes, which indicates that the proposed model with graph neural network can effectively describe various correlation structures in dialogue, thus contributing to the high-quality dialogue response generation.