System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning
System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic Reasoning
复制标题
DOI：
10.18653/v1/2022.findings-emnlp.42
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Wenyue Hua;Yongfeng Zhang
中科院分区：
文献类型：
--
作者：
Wenyue Hua;Yongfeng Zhang
逻辑推理对于许多当前的NLP神经网络模型来说是一个挑战，因为它需要的不仅仅是从数据中学习信息表示的能力。受认知科学中的双重过程理论的启发，该理论认为人类的认知过程包括两个阶段：依赖于感知的直观、无意识和快速过程，称为系统1，以及执行复杂推理的逻辑、有意识和缓慢的过程，称为系统2。我们利用神经逻辑推理(系统2)在表征学习模型(系统1)的基础上，在基础神经模型学习的表征之上进行显式的基于神经的可微逻辑推理。基于常识知识图完成任务的实验，我们证明了两系统体系结构总是比单独的System 1模型有所改进。实验还表明，规则驱动的逻辑正则化和数据驱动的值正则都很重要，在没有这两个正则化的情况下，性能的提高是微乎其微的，这表明从逻辑先验数据和训练数据中学习对于推理任务是重要的。
Logical reasoning is a challenge for many current NLP neural network models since it requires more than the ability of learning informative representations from data. Inspired by the Dual Process Theory in cognitive science — which proposes that human cognition process involves two stages: an intuitive, unconscious and fast process relying on perception called System 1, and a logical, conscious and slow process performing complex reasoning called System 2 — we leverage neural logic reasoning (System 2) on top of the representation learning models (System 1), which conducts explicit neural-based differentiable logical reasoning on top of the representations learned by the base neural models. Based on experiments on the commonsense knowledge graph completion task, we show that the two-system architecture always improves from its System 1 model alone. Experiments also show that both the rule-driven logical regularizer and the data-driven value regularizer are important and the performance improvement is marginal without the two regularizers, which indicates that learning from both logical prior and training data is important for reasoning tasks.