Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
This addresses the challenge of integrating symbolic reasoning with neural networks for scalable AI applications, though it appears incremental as it builds on existing KB representation methods.
The authors tackled the problem of representing symbolic knowledge bases for neural reasoning by introducing a sparse-matrix reified KB, which is fully differentiable, faithful to semantics, and scalable to tens of millions of entities, achieving competitive performance on KB completion and semantic parsing benchmarks.
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.