Combining symbolic human knowledge with neural networks provides a rule-based ante-hoc explanation of the output. In this paper, we propose feature extracting functions for integrating human knowledge abstracted as logic rules into the predictive behavior of a neural network. These functions are embodied as programming functions, which represent the applicable domain knowledge as a set of logical instructions and provide a modified distribution of independent features on input data. Unlike other existing neural logic approaches, the programmatic nature of these functions implies that they do not require any kind of special mathematical encoding, which makes our method very general and flexible in nature. We illustrate the performance of our approach for sentiment classification and compare our results to those obtained using two baselines.
翻译:将人类的象征性知识与神经网络结合起来,对输出提供了基于规则的预动动脉解释。在本文中,我们提出将人类知识作为逻辑规则纳入神经网络预测行为的特征提取功能。这些功能体现为编程功能,代表了可适用的域知识,作为一套逻辑指示,并提供了输入数据独立特征的经修改的分布。与其他现有的神经逻辑方法不同,这些功能的方案性质意味着它们不需要任何特殊的数学编码,这使得我们的方法非常笼统和灵活。我们举例说明了我们的情绪分类方法的绩效,并将我们的结果与使用两个基线获得的结果进行比较。