Символические правила
method
ID: symbolicrules
Related Papers
Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks
AbstractNeural networks can achieve impressive performance on many natural language processing applications, but they typically need large labeled data for training and are not easily interpretable. On the other hand, …...
Neuralizing Regular Expressions for Slot Filling
AbstractNeural models and symbolic rules such as regular expressions have their respective merits and weaknesses. In this paper, we study the integration of the two approaches for the slot filling …...