Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
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.
Also published in ICLR2020 https://openreview.net/forum?id=BJlguT4YPr¬eId=BJlguT4YPr
References in corpus (10)
- Distributed Representations of Words and Phrases and their Compositionality
- Semi-Supervised Classification with Graph Convolutional Networks
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- Improving Text-to-SQL Evaluation Methodology
- Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
- Embedding Logical Queries on Knowledge Graphs
- PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
- TensorLog: Deep Learning Meets Probabilistic DBs
- Generating Logical Forms from Graph Representations of Text and Entities
Cited by in corpus (6)
- Neuro-Symbolic Artificial Intelligence: Current Trends
- Reasoning Over Virtual Knowledge Bases With Open Predicate Relations
- Discriminative Reasoning for Document-level Relation Extraction
- SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
- Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection
- End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs