Letter-string analogy is an important analogy learning task which seems to be easy for humans but very challenging for machines. The main idea behind current approaches to solving letter-string analogies is to design heuristic rules for extracting analogy structures and constructing analogy mappings. However, one key problem is that it is difficult to build a comprehensive and exhaustive set of analogy structures which can fully describe the subtlety of analogies. This problem makes current approaches unable to handle complicated letter-string analogy problems. In this paper, we propose Neural logic analogy learning (Noan), which is a dynamic neural architecture driven by differentiable logic reasoning to solve analogy problems. Each analogy problem is converted into logical expressions consisting of logical variables and basic logical operations (AND, OR, and NOT). More specifically, Noan learns the logical variables as vector embeddings and learns each logical operation as a neural module. In this way, the model builds computational graph integrating neural network with logical reasoning to capture the internal logical structure of the input letter strings. The analogy learning problem then becomes a True/False evaluation problem of the logical expressions. Experiments show that our machine learning-based Noan approach outperforms state-of-the-art approaches on standard letter-string analogy benchmark datasets.
翻译:字母字符串类比是一个重要的类比学习任务,对于人类来说似乎很容易,但对于机器来说却非常具有挑战性。当前解决字母字符串类比的方法背后的主要理念是设计用于提取类比结构和构建类比绘图的超自然规则。然而,一个关键问题是,很难建立一套全面和详尽的类比结构,能够充分描述类比的微妙性。这个问题使得当前方法无法处理复杂的字母字符串类比问题。在本文中,我们提出神经逻辑类比学习(Noan),这是一个动态神经结构,由不同的逻辑推理驱动,解决类比问题。每个类比问题都被转换成逻辑表达方式,包括逻辑变量和基本逻辑操作(AND、OR和NOT)。更具体地说,Noan将逻辑变量作为矢量嵌学习,并将每种逻辑操作作为神经模块学习。在这种方式上,模型构建计算图表,将神经网络与逻辑推理,以捕捉取输入字母串联的内部逻辑结构。随后,类比学习问题成为逻辑表达方式的真/法评估问题。实验显示,我们的标准类比法方法是标准比法方法。