论文标题
在生成对话中控制风格
Controlling Style in Generated Dialogue
论文作者
论文摘要
使用具有数十亿个可训练参数的非常大的体系结构，开放域的对话模型已经擅长于产生自然的对话。培训这些体系结构所需的庞大培训数据汇总了许多不同的样式，音调和素质。使用该数据训练单个模型，因此很难将模型用作一致的对话代理，例如具有稳定的角色特征和典型的表达方式。已经提出了几种提供有关生成架构的控制机制的架构，每个建筑都有不同的权衡。但是，目前尚不清楚他们在对话中的使用是否可行，以及最新的最新对话体系结构的权衡是什么样的。在这项工作中，我们调整了三个先前提出的可控生成体系结构来开放域对话生成，控制了这一代的风格，以匹配大约200种可能的样式。我们比较它们各自的性能和权衡，并展示如何使用它们来提供对现有的对话数据集的见解，并生成各种样式的对话回复集。
Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many different styles, tones, and qualities. Using that data to train a single model makes it difficult to use the model as a consistent conversational agent, e.g. with a stable set of persona traits and a typical style of expression. Several architectures affording control mechanisms over generation architectures have been proposed, each with different trade-offs. However, it remains unclear whether their use in dialogue is viable, and what the trade-offs look like with the most recent state-of-the-art conversational architectures. In this work, we adapt three previously proposed controllable generation architectures to open-domain dialogue generation, controlling the style of the generation to match one among about 200 possible styles. We compare their respective performance and tradeoffs, and show how they can be used to provide insights into existing conversational datasets, and generate a varied set of styled conversation replies.
