2019, [arXiv]
Whats New It gives a framework to augment neuron with a rule from external knowledge, and proves its effectivenss specifically with the lesser training data.
Illustrative Example
Major Contribution
- Framework incorporating first-oder logic rules into neural network design
- Experiments on augmenting neural network with first order logic at following three levels:
- intermediate decisions (i.e. attentions);
- output decisions constrained by intermediate states *output decisions constrained using label dependencies
- Validation of the framework on three use cases
How It Works
-
Augmenting Attentions
-
Output decisions at Intermediate States
- As can be seen, it directly modifies output decision, it can take augemented attention as inputs.