Corpus ID: 220496138

Learning Reasoning Strategies in End-to-End Differentiable Proving

@article{Minervini2020LearningRS,
  title={Learning Reasoning Strategies in End-to-End Differentiable Proving},
  author={Pasquale Minervini and Sebastian Riedel and Pontus Stenetorp and Edward Grefenstette and Tim Rockt{\"a}schel},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.06477}
}
Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted by their computational complexity, as they need to consider all possible proof paths for… Expand

Figures and Tables from this paper

RNNLOGIC: LEARNING LOGIC RULES FOR REASON-
Logic Tensor Networks
Towards bridging the neuro-symbolic gap: deep deductive reasoners
Complex Query Answering with Neural Link Predictors
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability
Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Neural Markov Logic Networks
...
1
2
...

References

SHOWING 1-10 OF 60 REFERENCES
End-to-end Differentiable Proving
Differentiable Reasoning on Large Knowledge Bases and Natural Language
Programming with a Differentiable Forth Interpreter
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
Differentiable Learning of Logical Rules for Knowledge Base Reasoning
ReasoNet: Learning to Stop Reading in Machine Comprehension
Reconciling deep learning with symbolic artificial intelligence: representing objects and relations
...
1
2
3
4
5
...