论文标题
具有符号知识基础推理的可扩展神经方法
Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
论文作者
论文摘要
我们描述了一种新颖的方式来表示象征性知识基础（KB），称为稀疏的Matrix Repied KB。这种表示可以使神经模块完全差异化，忠于KB的原始语义，足以模拟多跳的推断，并且足以与现实的大型KB一起使用。稀疏的matrix redified KB可以分布在多个GPU上，可以扩展到数以千万计的实体和事实，并且比幼稚的稀疏 - 马trix实现更快。 REDIFIED KB使非常简单的端到端体系结构能够在代表两个任务家族的几个基准上获得竞争性能：KB完成和从表示的语义解析器。
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.
