Update README.md

README.md

@@ -29,14 +29,17 @@ inference: false
 
 **Metrics:**
 
-Read more about evaluation protocol & datasets in our [paper](https://arxiv.org/abs/2402.15343) and [blog post](https://www.numind.ai/blog/a-foundation-model-for-entity-recognition).
+Here is the aggregated performance of the models over several datasets.
+
+k=X means that as a training data, we took only X examples for each class, trained the model, and evaluated it on the full test set.
 
-| Model | F1 macro |
+| Model | k=1 | k=4 | k=16 | k=64 |
 |----------|----------|
-|   RoBERTa-base  |  0.7129   |
-|   ours  |   0.7500  |
-|   ours + two emb  |   0.7686  |
+|   RoBERTa-base  |  24.5   |   44.7 | 58.1 | 65.4
+|   RoBERTa-base + NER-BERT pre-training | 32.3 | 50.9 | 61.9 | 67.6 |
+|   NuNER v1.0  |   39.4 | 59.6 | 67.8 | 71.5 |
 
+Read more about evaluation protocol & datasets in our [paper](https://arxiv.org/abs/2402.15343) and [blog post](https://www.numind.ai/blog/a-foundation-model-for-entity-recognition).
 
 ## Usage