Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base

2020/02/14 by Cohen, William W., Sun, Haitian, Hofer, R. Alex +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2002.06115

Abstract

We describe a novel way of representing a symbolic knowledge base (KB) called a sparse-matrix reified KB. This representation enables neural modules that are fully differentiable, faithful to the original semantics of the KB, expressive enough to model multi-hop inferences, and scalable enough to use with realistically large KBs. The sparse-matrix reified KB can be distributed across multiple GPUs, can scale to tens of millions of entities and facts, and is orders of magnitude faster than naive sparse-matrix implementations. The reified KB enables very simple end-to-end architectures to obtain competitive performance on several benchmarks representing two families of tasks: KB completion, and learning semantic parsers from denotations.

Related

• Building Memory with Concept Learning Capabilities from Large-scale Knowledge Base
• Neural Query Language: A Knowledge Base Query Language for Tensorflow
• Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
• Scalable Coupling of Deep Learning with Logical Reasoning
• Neural Reasoning Networks: Efficient Interpretable Neural Networks With Automatic Textual Explanations