poltextlab
commited on
Commit
•
4bd6f40
1
Parent(s):
f31381d
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,23 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
Model description Cased fine-tuned BERT model for English, trained on (manually annotated) Hungarian parliamentary speeches scraped from parlament.hu, and translated with Google Translate API.
|
5 |
+
|
6 |
+
|
7 |
+
Training The fine-tuned version of the original bert-base-cased model (bert-base-cased), trained on HunEmPoli corpus, translated with Google Translate API.
|
8 |
+
|
9 |
+
|
10 |
+
The model can be used as any other (cased) BERT model. It has been tested recognizing emotions at the sentence level in (parliamentary) pre-agenda speeches, where:
|
11 |
+
|
12 |
+
'Label_0': Neutral
|
13 |
+
'Label_1': Fear
|
14 |
+
'Label_2': Sadness
|
15 |
+
'Label_3': Anger
|
16 |
+
'Label_4': Disgust
|
17 |
+
'Label_5': Success
|
18 |
+
'Label_6': Joy
|
19 |
+
'Label_7': Trust
|
20 |
+
|
21 |
+
|
22 |
+
Eval results
|
23 |
+
|