纵向对话中的响应生成：哪种知识表示有帮助？
Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?
AI总结：
本文研究纵向对话中的响应生成，通过微调 GePpeTto 和 iT5 并比较包括图表示在内的不同个人知识表示，结合自动指标、Integrated Gradients 和人工评估，分析哪种知识表示最能提升生成质量。
摘要：
纵向对话（LD）是人机对话系统中最具挑战性的对话类型。LD 包含在稀疏的对话会话序列中针对每个个体特定的事件回忆、个人想法和情感。为 LD 设计的对话系统应当在多个会话和长时间周期（例如数周）内与用户进行独特交互，并引导他们参与个人对话，以详细阐述他们的感受、想法和现实生活事件。在本文中，我们研究 LD 中的响应生成任务。我们评估通用预训练语言模型（PLM）是否适用于这一目的。我们使用 LD 数据集对两个 PLM——GePpeTto（GPT-2）和 iT5——进行微调。我们实验了从 LD 中提取的个人知识的不同表示形式，用于基于知识的响应生成，包括所提及事件和参与者的图表示。我们通过自动指标评估模型性能，并通过 Integrated Gradients 技术评估知识的贡献。我们通过对用户的语境化、适当性和参与度进行人工评估，对自然语言生成错误进行分类。
英文摘要：
Longitudinal Dialogues (LD) are the most challenging type of conversation for human-machine dialogue systems. LDs include the recollections of events, personal thoughts, and emotions specific to each individual in a sparse sequence of dialogue sessions. Dialogue systems designed for LDs should uniquely interact with the users over multiple sessions and long periods of time (e.g. weeks), and engage them in personal dialogues to elaborate on their feelings, thoughts, and real-life events. In this paper, we study the task of response generation in LDs. We evaluate whether general-purpose Pre-trained Language Models (PLM) are appropriate for this purpose. We fine-tune two PLMs, GePpeTto (GPT-2) and iT5, using a dataset of LDs. We experiment with different representations of the personal knowledge extracted from LDs for grounded response generation, including the graph representation of the mentioned events and participants. We evaluate the performance of the models via automatic metrics and the contribution of the knowledge via the Integrated Gradients technique. We categorize the natural language generation errors via human evaluations of contextualization, appropriateness and engagement of the user.
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。
