arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.04707cs.AIcs.CLcs.SC
收藏

语境理解的神经符号结构

Neuro-symbolic Architectures for Context Understanding

Bosch Research and Technology Center(博世研究与技术中心);Carnegie Mellon University(卡内基梅隆大学);University of South Carolina(南卡罗来纳大学)

Alessandro Oltramari, Jonathan Francis, Cory Henson, Kaixin Ma, Ruwan Wickramarachchi

摘要:

计算上下文理解是指代理融合不同信息源进行决策的能力,因此通常被视为复杂机器推理能力(例如人工智能(AI))的先决条件。数据驱动和知识驱动方法是追求这种机器意义生成能力的两种经典技术。然而,虽然数据驱动的方法试图通过在现实世界中进行观察来模拟事件的统计数据,但它们仍然难以解释,并且缺乏自然整合外部知识的机制。相反,知识驱动的方法,结合结构化的知识库,执行基于公理化原则的符号推理,并在其推理过程中更具解释性,但是,他们往往缺乏估计的统计显着性的推理能力。为了解决这些问题,我们建议使用混合人工智能方法作为综合两种方法优势的通用框架。具体来说,我们继承了神经符号的概念,作为使用知识库来指导深度神经网络学习过程的一种方式。我们进一步接地我们的讨论中的两个应用程序的神经符号,并在这两种情况下,表明我们的系统保持可解释性,同时实现可比的性能,相对于国家的最先进的。

英文摘要:

Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as in artificial intelligence (AI). Data-driven and knowledge-driven methods are two classical techniques in the pursuit of such machine sense-making capability. However, while data-driven methods seek to model the statistical regularities of events by making observations in the real-world, they remain difficult to interpret and they lack mechanisms for naturally incorporating external knowledge. Conversely, knowledge-driven methods, combine structured knowledge bases, perform symbolic reasoning based on axiomatic principles, and are more interpretable in their inferential processing; however, they often lack the ability to estimate the statistical salience of an inference. To combat these issues, we propose the use of hybrid AI methodology as a general framework for combining the strengths of both approaches. Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks. We further ground our discussion in two applications of neuro-symbolism and, in both cases, show that our systems maintain interpretability while achieving comparable performance, relative to the state-of-the-art.

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。

↑