用神经规则引擎实现符号知识的泛化
Generalize Symbolic Knowledge With Neural Rule Engine
摘要:
由于神经网络在许多自然语言处理任务中占据了主导地位,因此通过整合符号知识来提高神经网络模型的性能引起了人们的广泛关注。与已有的研究不同,本文从知识驱动的角度探讨了这两种范式的结合。我们提出了神经规则引擎(NRE),它可以从逻辑规则中显式地学习知识,然后用神经网络隐式地概括它们。NRE用神经模块网络实现,其中每个模块代表逻辑规则的动作。实验结果表明,NRE能显著提高逻辑规则的泛化能力,并能显著提高召回率。同时,精度仍然保持在较高水平。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。