Pat-in-the-loop: Syntax-based neural networks with activation visualization and declarative control

The dazzling success of neural networks over natural language processing systems is imposing a urgent need to control their behavior with simpler, more direct declarative rules. In this paper, we propose Pat-in-the-loop as a model to control a specific class of syntax-oriented neural networks by adding declarative rules. In Pat-in-the-loop, distributed tree encoders allow to exploit parse trees in neural networks, heat parse trees visualize activation of parse trees, and parse subtrees are used as declarative rules in the neural network. A pilot study on question classification showed that declarative rules representing human knowledge can be effectively used in these neural networks.3