Previous question-answer pair generation methods aimed to produce fluent and meaningful question-answer pairs but tend to have poor diversity. Recent attempts addressing this issue suffer from either low model capacity or overcomplicated architecture. Furthermore, they overlooked the problem where the controllability of their models is highly dependent on the input. In this paper, we propose a model named VOLTA that enhances generative diversity by leveraging the Variational Autoencoder framework with a shared backbone network as its encoder and decoder. In addition, we propose adding InfoGAN-style latent codes to enable input-independent controllability over the generation process. We perform comprehensive experiments and the results show that our approach can significantly improve diversity and controllability over state-of-the-art models.

翻译：摘要：以往的问答对生成方法旨在生成流畅且有意义的问答对，但往往缺乏多样性。近期针对此问题的尝试要么存在模型容量不足，要么架构过于复杂。此外，这些方法忽略了模型可控性高度依赖输入的问题。本文提出一种名为VOLTA的模型，通过采用变分自编码器框架并共享骨干网络作为其编码器和解码器来增强生成多样性。同时，我们提出添加InfoGAN风格的潜在编码，以实现对生成过程的输入无关可控性。通过全面实验，结果表明我们的方法在多样性和可控性上显著优于现有最优模型。