Differentiable Representations For Multihop Inference Rules
arXiv:1905.10417
Abstract
We present efficient differentiable implementations of second-order multi-hop reasoning using a large symbolic knowledge base (KB). We introduce a new operation which can be used to compositionally construct second-order multi-hop templates in a neural model, and evaluate a number of alternative implementations, with different time and memory trade offs. These techniques scale to KBs with millions of entities and tens of millions of triples, and lead to simple models with competitive performance on several learning tasks requiring multi-hop reasoning.
References in corpus (12)
- 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
- Order Matters: Sequence to sequence for sets
- Variational Reasoning for Question Answering with Knowledge Graph
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
- Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
- Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
- TensorLog: Deep Learning Meets Probabilistic DBs
- Sketching and Neural Networks
- Neural Compositional Denotational Semantics for Question Answering