Add evaluation results on masakhaner dataset
#1
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
- swa
|
4 |
tags:
|
5 |
- NER
|
@@ -11,7 +11,40 @@ metrics:
|
|
11 |
- recall
|
12 |
license: apache-2.0
|
13 |
widget:
|
14 |
-
- text:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
---
|
16 |
|
17 |
# Model description
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
- swa
|
4 |
tags:
|
5 |
- NER
|
|
|
11 |
- recall
|
12 |
license: apache-2.0
|
13 |
widget:
|
14 |
+
- text: Wizara ya afya ya Tanzania imeripoti Jumatatu kuwa, watu takriban 14 zaidi
|
15 |
+
wamepata maambukizi ya Covid-19.
|
16 |
+
model-index:
|
17 |
+
- name: arnolfokam/mbert-base-uncased-ner-swa
|
18 |
+
results:
|
19 |
+
- task:
|
20 |
+
type: token-classification
|
21 |
+
name: Token Classification
|
22 |
+
dataset:
|
23 |
+
name: masakhaner
|
24 |
+
type: masakhaner
|
25 |
+
config: swa
|
26 |
+
split: test
|
27 |
+
metrics:
|
28 |
+
- name: Accuracy
|
29 |
+
type: accuracy
|
30 |
+
value: 0.9478152826672189
|
31 |
+
verified: true
|
32 |
+
- name: Precision
|
33 |
+
type: precision
|
34 |
+
value: 0.956198880757641
|
35 |
+
verified: true
|
36 |
+
- name: Recall
|
37 |
+
type: recall
|
38 |
+
value: 0.9524405059672694
|
39 |
+
verified: true
|
40 |
+
- name: F1
|
41 |
+
type: f1
|
42 |
+
value: 0.9543159929827074
|
43 |
+
verified: true
|
44 |
+
- name: loss
|
45 |
+
type: loss
|
46 |
+
value: 0.38853195309638977
|
47 |
+
verified: true
|
48 |
---
|
49 |
|
50 |
# Model description
|