This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on the Webis-Clickbait-17 dataset. It achieves the following results on the evaluation set:
Loss: 0.0261
The following list presents the current performances achieved by the participants. As primary evaluation measure, Mean Squared Error (MSE) with respect to the mean judgments of the annotators is used. Our result is 0,0261 for the MSE metric. We do not compute the other metrics. We try not to cheat using unknown data at the time of the challenge. We do not use k-fold cross validation techniques.
| team | MSE | F1 | Precision | Recall | Accuracy | Runtime |
|---|---|---|---|---|---|---|
| goldfish | 0.024 | 0.741 | 0.739 | 0.742 | 0.876 | 16:20:21 |
| caush | 0.026 | 00:11:00 | ||||
| monkfish | 0.026 | 0.694 | 0.785 | 0.622 | 0.870 | 03:41:35 |
| dartfish | 0.027 | 0.706 | 0.733 | 0.681 | 0.865 | 00:47:07 |
| torpedo19 | 0.03 | 0.677 | 0.755 | 0.614 | 0.861 | 00:52:44 |
| albacore | 0.031 | 0.67 | 0.731 | 0.62 | 0.855 | 00:01:10 |
| blobfish | 0.032 | 0.646 | 0.738 | 0.574 | 0.85 | 00:03:22 |
| zingel | 0.033 | 0.683 | 0.719 | 0.65 | 0.856 | 00:03:27 |
| anchovy | 0.034 | 0.68 | 0.717 | 0.645 | 0.855 | 00:07:20 |
| ray | 0.034 | 0.684 | 0.691 | 0.677 | 0.851 | 00:29:28 |
| icarfish | 0.035 | 0.621 | 0.768 | 0.522 | 0.849 | 01:02:57 |
| emperor | 0.036 | 0.641 | 0.714 | 0.581 | 0.845 | 00:04:03 |
| carpetshark | 0.036 | 0.638 | 0.728 | 0.568 | 0.847 | 00:08:05 |
| electriceel | 0.038 | 0.588 | 0.727 | 0.493 | 0.835 | 01:04:54 |
| arowana | 0.039 | 0.656 | 0.659 | 0.654 | 0.837 | 00:35:24 |
| pineapplefish | 0.041 | 0.631 | 0.642 | 0.621 | 0.827 | 00:54:28 |
| whitebait | 0.043 | 0.565 | 0.7 | 0.474 | 0.826 | 00:04:31 |
