Generalize Symbolic Knowledge With Neural Rule Engine
This addresses the challenge of combining symbolic and neural paradigms for NLP tasks, offering a novel approach that is incremental in its method.
The paper tackled the problem of integrating symbolic knowledge into neural networks to improve performance, proposing Neural Rule Engine (NRE) to learn from logic rules and generalize them, resulting in a significant increase in recall while maintaining high precision.
As neural networks have dominated the state-of-the-art results in a wide range of NLP tasks, it attracts considerable attention to improve the performance of neural models by integrating symbolic knowledge. Different from existing works, this paper investigates the combination of these two powerful paradigms from the knowledge-driven side. We propose Neural Rule Engine (NRE), which can learn knowledge explicitly from logic rules and then generalize them implicitly with neural networks. NRE is implemented with neural module networks in which each module represents an action of a logic rule. The experiments show that NRE could greatly improve the generalization abilities of logic rules with a significant increase in recall. Meanwhile, the precision is still maintained at a high level.