Explicitly modeling emotions in dialogue generation has important applications, such as building empathetic personal companions. In this study, we consider the task of expressing a specific emotion for dialogue generation. Previous approaches take the emotion as an input signal, which may be ignored during inference. We instead propose a search-based emotional dialogue system by simulated annealing (SA). Specifically, we first define a scoring function that combines contextual coherence and emotional correctness. Then, SA iteratively edits a general response and searches for a sentence with a higher score, enforcing the presence of the desired emotion. We evaluate our system on the NLPCC2017 dataset. Our proposed method shows 12% improvements in emotion accuracy compared with the previous state-of-the-art method, without hurting the generation quality (measured by BLEU).

翻译：在对话生成过程中明确模拟情感具有重要的应用,例如建立同情的个人伴侣。在本研究中,我们考虑了为对话生成表达特定情感的任务。以前的方法将情感作为一种输入信号,在推论期间可能会被忽略。相反,我们提议通过模拟肛交(SA)来建立基于搜索的情感对话系统。具体地说,我们首先定义一个将背景一致性和情感正确性结合起来的评分功能。然后,SA反复编辑一个一般性回应,并搜索一个高分的句子,以强化所希望的情感的存在。我们在NLPCC2017数据集中评估了我们的系统。我们建议的方法显示,与以前最先进的方法相比,情感准确性提高了12%,而没有伤害生成质量(BLEU衡量的)。