Original Pdf: pdf
Data: [MetaQA](https://paperswithcode.com/dataset/metaqa), [NELL-995](https://paperswithcode.com/dataset/nell-995), [WebQuestions](https://paperswithcode.com/dataset/webquestions), [WebQuestionsSP](https://paperswithcode.com/dataset/webquestionssp)
TL;DR: A scalable differentiable neural module that implements reasoning on symbolic KBs.
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.
Keywords: question-answering, knowledge base completion, neuro-symbolic reasoning, multihop reasoning