Commit
•
1a7a557
1
Parent(s):
e05fee7
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,8 +39,9 @@ k=X means that as training data, we took only X examples for each class, trained
|
|
| 39 |
|----------|----------|----------|----------|----------|
|
| 40 |
| RoBERTa-base | 24.5 | 44.7 | 58.1 | 65.4
|
| 41 |
| RoBERTa-base + NER-BERT pre-training | 32.3 | 50.9 | 61.9 | 67.6 |
|
|
|
|
| 42 |
| NuNER v1.0 | 39.4 | 59.6 | 67.8 | 71.5 |
|
| 43 |
-
| NuNER v2.0 | **43.6** | **61.0** | **68.2** | **72.0** |
|
| 44 |
|
| 45 |
NuNER v1.0 has similar performance to 7B LLMs (70 times bigger than NuNER v1.0) created specifically for the NER task. Thus NuNER v2.0 should be even better than the 7b LLM.
|
| 46 |
|
|
|
|
| 39 |
|----------|----------|----------|----------|----------|
|
| 40 |
| RoBERTa-base | 24.5 | 44.7 | 58.1 | 65.4
|
| 41 |
| RoBERTa-base + NER-BERT pre-training | 32.3 | 50.9 | 61.9 | 67.6 |
|
| 42 |
+
| NuNER v0.1 | 34.3 | 54.6 | 64.0 | 68.7 |
|
| 43 |
| NuNER v1.0 | 39.4 | 59.6 | 67.8 | 71.5 |
|
| 44 |
+
| **NuNER v2.0** | **43.6** | **61.0** | **68.2** | **72.0** |
|
| 45 |
|
| 46 |
NuNER v1.0 has similar performance to 7B LLMs (70 times bigger than NuNER v1.0) created specifically for the NER task. Thus NuNER v2.0 should be even better than the 7b LLM.
|
| 47 |
|