学习用于个性化对话生成的检索增强
Learning Retrieval Augmentation for Personalized Dialogue Generation
AI总结：
针对人物画像信息不足导致个性化对话生成困难的问题，提出LAPDOG模型，通过联合训练故事检索器与对话生成器，利用外部故事文档增强人物画像，在CONVAI2数据集上显著优于基线。
摘要：
个性化对话生成专注于通过利用人物画像和对话上下文生成高度定制的回复，在对话式AI应用中获得了显著关注。然而，当前个性化对话数据集中普遍存在的人物画像设置通常仅包含四到五句话，可能无法提供关于智能体的全面描述，对生成真正个性化的对话构成了挑战。为处理此问题，我们提出了学习用于个性化对话生成的检索增强（LAPDOG），研究利用外部知识进行人物画像对话生成的潜力。具体而言，提出的LAPDOG模型由故事检索器和对话生成器组成。故事检索器使用给定的人物画像作为查询，从故事文档中检索相关信息，作为补充上下文以增强人物画像。对话生成器利用对话历史和增强后的人物画像来生成个性化回复。为了优化，我们采用了一个联合训练框架，协同学习故事检索器和对话生成器，其中故事检索器朝向期望的最终指标（例如，BLEU）进行优化，以为对话生成器检索内容以生成个性化回复。在以ROCStory作为补充数据源的CONVAI2数据集上进行的实验表明，提出的LAPDOG方法显著优于基线，表明了所提方法的有效性。LAPDOG模型代码已公开供进一步探索。https://github.com/hqsiswiliam/LAPDOG
英文摘要：
Personalized dialogue generation, focusing on generating highly tailored responses by leveraging persona profiles and dialogue context, has gained significant attention in conversational AI applications. However, persona profiles, a prevalent setting in current personalized dialogue datasets, typically composed of merely four to five sentences, may not offer comprehensive descriptions of the persona about the agent, posing a challenge to generate truly personalized dialogues. To handle this problem, we propose $\textbf{L}$earning Retrieval $\textbf{A}$ugmentation for $\textbf{P}$ersonalized $\textbf{D}$ial$\textbf{O}$gue $\textbf{G}$eneration ($\textbf{LAPDOG}$), which studies the potential of leveraging external knowledge for persona dialogue generation. Specifically, the proposed LAPDOG model consists of a story retriever and a dialogue generator. The story retriever uses a given persona profile as queries to retrieve relevant information from the story document, which serves as a supplementary context to augment the persona profile. The dialogue generator utilizes both the dialogue history and the augmented persona profile to generate personalized responses. For optimization, we adopt a joint training framework that collaboratively learns the story retriever and dialogue generator, where the story retriever is optimized towards desired ultimate metrics (e.g., BLEU) to retrieve content for the dialogue generator to generate personalized responses. Experiments conducted on the CONVAI2 dataset with ROCStory as a supplementary data source show that the proposed LAPDOG method substantially outperforms the baselines, indicating the effectiveness of the proposed method. The LAPDOG model code is publicly available for further exploration. https://github.com/hqsiswiliam/LAPDOG
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
