saattrupdan
commited on
Commit
•
996a623
1
Parent(s):
daef20d
Update README.md
Browse files
README.md
CHANGED
@@ -1,15 +1,28 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
-
-
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
-
- name: nbailab-base-ner-scandi
|
9 |
results:
|
10 |
- task:
|
11 |
name: Token Classification
|
12 |
type: token-classification
|
|
|
|
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,8 +30,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# nbailab-base-ner-scandi-unbalanced
|
19 |
|
20 |
-
This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) on the
|
21 |
-
It achieves the following results on
|
22 |
- Loss: 0.0666
|
23 |
- Micro F1: 0.8693
|
24 |
- Micro F1 No Misc: 0.8925
|
1 |
---
|
2 |
+
language:
|
3 |
+
- da
|
4 |
+
- no
|
5 |
+
- nb
|
6 |
+
- nn
|
7 |
+
- sv
|
8 |
+
- fo
|
9 |
+
- is
|
10 |
+
license: mit
|
11 |
tags:
|
12 |
- generated_from_trainer
|
13 |
datasets:
|
14 |
+
- dane
|
15 |
+
- norne
|
16 |
+
- wikiann
|
17 |
+
- suc3.0
|
18 |
model-index:
|
19 |
+
- name: nbailab-base-ner-scandi
|
20 |
results:
|
21 |
- task:
|
22 |
name: Token Classification
|
23 |
type: token-classification
|
24 |
+
widget:
|
25 |
+
- "Hans er en professor på IT Universitetet i København, og han er en rigtig københavner. Hans kat, altså Hans' kat, Lisa, er supersød. Han fik købt en Mona Lisa på tilbud i Netto og gav den til hans kat, og nu er Mona Lisa Lisa's kæreste eje. Hans er med hans bror Peter, og de besluttede, at Peterskirken skulle have fint besøg af Peter og hans ven Hans."
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
|
31 |
# nbailab-base-ner-scandi-unbalanced
|
32 |
|
33 |
+
This model is a fine-tuned version of [NbAiLab/nb-bert-base](https://huggingface.co/NbAiLab/nb-bert-base) on the concatenation of DaNE, NorNE, SUC 3.0 and the Icelandic and Faroese parts of the WikiAnn dataset.
|
34 |
+
It achieves the following results on DaNE:
|
35 |
- Loss: 0.0666
|
36 |
- Micro F1: 0.8693
|
37 |
- Micro F1 No Misc: 0.8925
|