The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during the decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories. In this paper, we propose a generic diversity-promoting joint network, called Holistic Semantic Constraint Joint Network (HSCJN), enhancing the global sentence information, and then regularizing the objective function with penalizing the low entropy output during the training stage. Our network introduces more target information to improve diversity and captures direct semantic information to better constrain relevance simultaneously. Moreover, the proposed method can be easily applied to any Seq2Seq structure. Extensive experiments on several dialogue corpuses show that our method effectively improves both semantic consistency and diversity of generated responses, and achieves better performance than other competitive methods.

序列到序列（Seq2Seq）模型在解码过程中给定先前观察到的单词时会迭代生成目标单词，这会导致目标响应中整体语义的丢失以及响应和对话历史之间完整的语义关系。在本文中，我们提出了一种通用的，促进多样性的联合网络，称为整体语义约束联合网络（HSCJN），它增强了全局句子信息，然后在训练阶段对目标函数进行了正则化，并对低熵输出进行了惩罚。我们的网络引入了更多目标信息以改善多样性，并捕获直接语义信息以同时更好地约束相关性。而且，所提出的方法可以容易地应用于任何Seq2Seq结构。