This paper introduces a novel neuro-symbolic architecture for relation classification (RC) that combines rule-based methods with contemporary deep learning techniques. This approach capitalizes on the strengths of both paradigms: the adaptability of rule-based systems and the generalization power of neural networks. Our architecture consists of two components: a declarative rule-based model for transparent classification and a neural component to enhance rule generalizability through semantic text matching. Notably, our semantic matcher is trained in an unsupervised domain-agnostic way, solely with synthetic data. Further, these components are loosely coupled, allowing for rule modifications without retraining the semantic matcher. In our evaluation, we focused on two few-shot relation classification datasets: Few-Shot TACRED and a Few-Shot version of NYT29. We show that our proposed method outperforms previous state-of-the-art models in three out of four settings, despite not seeing any human-annotated training data. Further, we show that our approach remains modular and pliable, i.e., the corresponding rules can be locally modified to improve the overall model. Human interventions to the rules for the TACRED relation \texttt{org:parents} boost the performance on that relation by as much as 26\% relative improvement, without negatively impacting the other relations, and without retraining the semantic matching component.

翻译：本文提出了一种新颖的神经符号架构用于关系分类（RC），该架构将基于规则的方法与当代深度学习技术相结合。这种方法充分利用了两种范式的优势：基于规则系统的适应性和神经网络的泛化能力。我们的架构由两个组件组成：一个用于透明分类的声明性规则模型和一个通过语义文本匹配增强规则泛化能力的神经组件。值得注意的是，我们的语义匹配器以无监督的领域无关方式训练，仅使用合成数据。此外，这些组件是松散耦合的，允许在不重新训练语义匹配器的情况下修改规则。在评估中，我们聚焦于两个少样本关系分类数据集：Few-Shot TACRED 和 Few-Shot 版本的 NYT29。结果表明，尽管未使用任何人工标注的训练数据，我们提出的方法在四分之三的设置下优于先前的最先进模型。此外，我们证明该方法保持模块化和灵活性，即可以通过局部修改相应规则来改善整体模型。针对TACRED关系`org:parents`的规则进行人工干预后，该关系的性能相对提升了26%，且未对其他关系产生负面影响，也无需重新训练语义匹配组件。