使用逻辑推理和相关性评分的检索增强神经响应生成
Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoring
AI总结：
本文提出一种结合检索增强语言模型与逻辑推理的知识基础响应生成方法，通过概率逻辑编程丰富知识图谱并利用神经模型评分筛选关键元素，有效提升了任务导向对话系统响应的事实性与流畅性。
摘要：
在任务导向对话系统中构建响应通常依赖于诸如当前对话状态或外部数据库等信息源。本文提出了一种基于知识基础响应生成的新方法，该方法将检索增强语言模型与逻辑推理相结合。该方法围绕一个表示当前对话状态和背景信息的知识图谱展开，并分三步进行。首先，使用概率逻辑编程推断出的逻辑推导事实来丰富知识图谱。然后，在每一轮对话中，使用神经模型对该扩展图谱的每个节点和边的对话相关性进行评分。最后，将相关性得分最高的元素转换为自然语言形式，并整合到用于生成系统响应的神经对话模型的提示中。我们在两个数据集（KVRET 和 GraphWOZ）上研究了所提方法的益处，并进行了人工评估。实验结果表明，（概率）逻辑推理与对话相关性评分的结合确实提高了响应的事实性和流畅性。
英文摘要：
Constructing responses in task-oriented dialogue systems typically relies on information sources such the current dialogue state or external databases. This paper presents a novel approach to knowledge-grounded response generation that combines retrieval-augmented language models with logical reasoning. The approach revolves around a knowledge graph representing the current dialogue state and background information, and proceeds in three steps. The knowledge graph is first enriched with logically derived facts inferred using probabilistic logical programming. A neural model is then employed at each turn to score the conversational relevance of each node and edge of this extended graph. Finally, the elements with highest relevance scores are converted to a natural language form, and are integrated into the prompt for the neural conversational model employed to generate the system response. We investigate the benefits of the proposed approach on two datasets (KVRET and GraphWOZ) along with a human evaluation. Experimental results show that the combination of (probabilistic) logical reasoning with conversational relevance scoring does increase both the factuality and fluency of the responses.
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。
