We use the code provided by the original paper authors.
In our experiments, we use the same set of hyperparameters as the original work, but replace the default BERT encoder with our RuleTaker fine-tuned BERT.
We use the code provided by the original paper authors.
In our experiments, we use the same set of hyperparameters as the original work, but replace the default BERT encoder with our RuleTaker fine-tuned BERT.