PK-ICR：用于扎根对话的角色设定-知识交互式上下文检索
PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue
AI总结：
针对多上下文扎根对话中联合识别角色设定与知识的问题，提出可同时利用全部对话上下文、基于神经问答检索的低计算量方法PK-ICR，并设计零正例排序测试评估难负例排序性能。
摘要：
识别相关角色设定或知识，对于对话系统的扎根对话回复生成至关重要。然而，各类扎根依据大多是被孤立研究的，而近期工作引入了更具实际意义的多上下文对话任务。我们将“角色设定与知识双上下文识别”定义为针对给定对话联合识别角色设定和知识的任务，该任务在复杂的多上下文对话场景中可能具有更高的重要性。我们开发了一种新颖的扎根依据检索方法，可同时利用对话的全部上下文。该方法通过利用神经问答检索模型，所需计算资源更少。我们还进一步提出了新颖的零正例排序测试，用于衡量在语义不相似样本（即难负例）上相对于数据增强的排序性能。
英文摘要：
Identifying relevant persona or knowledge for conversational systems is critical to grounded dialogue response generation. However, each grounding has been mostly researched in isolation with more practical multi-context dialogue tasks introduced in recent works. We define Persona and Knowledge Dual Context Identification as the task to identify persona and knowledge jointly for a given dialogue, which could be of elevated importance in complex multi-context dialogue settings. We develop a novel grounding retrieval method that utilizes all contexts of dialogue simultaneously. Our method requires less computational power via utilizing neural QA retrieval models. We further introduce our novel null-positive rank test which measures ranking performance on semantically dissimilar samples (i.e. hard negatives) in relation to data augmentation.
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。
