The personalized dialogue explores the consistent relationship between dialogue generation and personality. Existing personalized dialogue agents model persona profiles from three resources: sparse or dense persona descriptions and dialogue histories. However, sparse structured persona attributes are explicit but uninformative, dense persona texts contain rich persona descriptions with much noise, and dialogue history query is both noisy and uninformative for persona modeling. In this work, we combine the advantages of the three resources to obtain a richer and more accurate persona. We design a Contrastive Latent Variable-based model (CLV) that clusters the dense persona descriptions into sparse categories, which are combined with the history query to generate personalized responses. Experimental results on Chinese and English datasets demonstrate our model's superiority in personalization.

翻译：个性化对话探讨了对话生成与个性之间的一致性关系。现有个性化对话代理从三种资源中建模人物画像：稀疏或密集的人物设定描述以及对话历史。然而，稀疏的结构化人物属性虽明确但信息量不足，密集的人物文本包含丰富的人物描述却伴有大量噪声，而对话历史查询在人物建模中既存在噪声又信息匮乏。在本工作中，我们结合这三种资源的优势，以获取更丰富且更准确的人物设定。我们设计了一种基于对比潜在变量的模型（CLV），该模型将密集人物描述聚类为稀疏类别，并将其与历史查询相结合，以生成个性化回复。在中英文数据集上的实验结果表明，我们的模型在个性化方面具有优越性。