In this article, conditional-transforming variational autoencoders (CTVAEs) are proposed for generating diverse short text conversations. In conditional variational autoencoders (CVAEs), the prior distribution of latent variable z follows a multivariate Gaussian distribution with mean and variance modulated by the input conditions. Previous work found that this distribution tended to become condition-independent in practical applications. Thus, this article designs CTVAEs to enhance the influence of conditions in CVAEs. In a CTVAE model, the latent variable z is sampled by performing a non-linear transformation on the combination of the input conditions and the samples from a condition-independent prior distribution N (0, I). In our experiments using a Chinese Sina Weibo dataset, the CTVAE model derives z samples for decoding with better condition-dependency than that of the CVAE model. The earth mover’s distance (EMD) between the distributions of the latent variable z at the training stage, and the testing stage is also reduced by using the CTVAE model. In subjective preference tests, our proposed CTVAE model performs significantly better than CVAE and sequence-to-sequence (Seq2Seq) models on generating diverse, informative, and topic-relevant responses.

中文翻译：

---

用于生成不同短文本对话的条件转换变分自动编码器

在本文中，提出了条件转换变分自动编码器 (CTVAE) 来生成各种短文本对话。在条件变分自动编码器 (CVAE) 中，潜在变量 z 的先验分布遵循多元高斯分布，均值和方差由输入条件调制。以前的工作发现，这种分布在实际应用中往往变得与条件无关。因此，本文设计 CTVAE 以增强 CVAE 中条件的影响。在 CTVAE 模型中，潜变量 z 通过对输入条件和来自与条件无关的先验分布 N (0, I) 的样本的组合执行非线性变换来采样。在我们使用中文新浪微博数据集的实验中，与 CVAE 模型相比，CTVAE 模型以更好的条件依赖性导出 z 个样本用于解码。通过使用 CTVAE 模型，在训练阶段和测试阶段的潜变量 z 的分布之间的推土机距离 (EMD) 也被减小了。在主观偏好测试中，我们提出的 CTVAE 模型在生成多样化、信息丰富和主题相关的响应方面明显优于 CVAE 和序列到序列 (Seq2Seq) 模型。