Abstract
The rapid advancement in artificial intelligence (AI), particularly through deep neural networks, has catalyzed significant progress in fields such as vision and text processing. Nonetheless, the pursuit of AI systems that exhibit human-like reasoning and interpretability continues to pose a substantial challenge. The Neural-Symbolic paradigm, which integrates the deep learning prowess of neural networks with the reasoning capabilities of symbolic systems, presents a promising pathway toward developing more transparent and comprehensible AI systems. Within this paradigm, the Knowledge Graph (KG) emerges as a crucial element, offering a structured and dynamic method for representing knowledge through interconnected entities and relationships, predominantly utilizing the triple (subject, predicate, object). This paper explores recent advancements in neural-symbolic integration based on KG, elucidating how KG underpins this integration across three key categories: enhancing the reasoning and interpretability of neural networks through the incorporation of symbolic knowledge (Symbol for Neural), refining the completeness and accuracy of symbolic systems via neural network methodologies (Neural for Symbol), and facilitating their combined application in Hybrid Neural-Symbolic Integration. It highlights current trends and proposes directions for future research in the domain of Neural-Symbolic AI.
Abstract (translated)
人工智能(AI)的快速发展,特别是通过深度神经网络,在视觉和文本处理等领域取得了显著的进步。然而,追求具有类人推理和可解释性的AI系统仍然是一个巨大的挑战。神经符号范式将神经网络的深度学习能力与符号系统的推理能力相结合,为开发更透明和可解释的AI系统提供了有益的途径。在这种范式中,知识图(KG)成为了一个关键要素,它通过连接实体和关系提供了一个结构化和动态的方法来表示知识,主要利用三元组(主体,谓词,对象)。本文探讨了基于KG的神经符号整合最近的研究进展,解释了KG如何通过引入符号知识(Symbol for Neural)来提高神经网络的推理和可解释性,通过神经网络方法论(Neural for Symbol)来优化符号系统的完整性准确性,并通过混合神经-符号整合来促进它们的联合应用。它强调了当前领域内的趋势,并提出了未来在神经符号AI领域的研究方向。
URL
https://arxiv.org/abs/2405.03524