Evaluation plan

Task A: We will use Multi-label Accuracy, Hamming loss and F1 (Micro, Macro, Weighted) for ranking the results. The ranking will be based on the Macro F1 score.

Task B: We will use Accuracy and F1 for ranking of the results. ROC-AUC will also be posted for teams where confidence scores are provided but will not be defining in the final ranking.