A Experiment Details for Reproducibility

For all the other datasets, we follow their original train/dev/test splits. We fine-tune a pre-trained language model (e.g., BERT -Base) over the source training set to generate the source model. Source test set is used for evaluating the "source F1" Statistics of each dataset pair are included in Table 9. Batch size is set to be 32 in all experiments for all the methods. We conduct grid search on learning rate and regularization strength for each experiment using the target dev set. Then we train the model using this hyper-parameter configuration with two additional random seeds and report the mean and standard deviation.