论文标题
用于多样化对话的相等大小的硬em算法
An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
论文作者
论文摘要
开放式对话系统旨在以开放式的方式通过自然语言文本与人类互动。尽管最近超级大对话系统（例如Chatgpt）取得了成功，但使用中等大小的对话系统仍然是普遍的实践，因为它们更轻巧且易于使用。但是，产生多种对话响应是具有挑战性的，尤其是在较小的模型中。在这项工作中，我们提出了相等大小的艰难期望 - 最大化（EQHARD-EM）算法，以训练多个二十座模型，以实现多样化的对话生成。我们的算法以艰苦的方式将样品分配给解码器，并施加等同的约束，以确保所有解码器都经过良好的训练。我们提供详细的理论分析以证明我们的方法是合理的。此外，对两个大规模开放域对话数据集进行了实验，验证了我们的eqhard-em算法是否会产生高质量的不同响应。
Open-domain dialogue systems aim to interact with humans through natural language texts in an open-ended fashion. Despite the recent success of super large dialogue systems such as ChatGPT, using medium-to-small-sized dialogue systems remains the common practice as they are more lightweight and accessible; however, generating diverse dialogue responses is challenging, especially with smaller models. In this work, we propose an Equal-size Hard Expectation--Maximization (EqHard-EM) algorithm to train a multi-decoder model for diverse dialogue generation. Our algorithm assigns a sample to a decoder in a hard manner and additionally imposes an equal-assignment constraint to ensure that all decoders are well-trained. We provide detailed theoretical analysis to justify our approach. Further, experiments on two large-scale open-domain dialogue datasets verify that our EqHard-EM algorithm generates high-quality diverse responses.
