ComPathos acknow
Browse files
README.md
CHANGED
|
@@ -39,6 +39,8 @@ model-index:
|
|
| 39 |
This model is a fine-tuned version of [dkleczek/bert-base-polish-cased-v1](https://huggingface.co/dkleczek/bert-base-polish-cased-v1) to predict 3-categorical sentiment.
|
| 40 |
Fine-tuned on 1k sample of manually annotated Twitter data.
|
| 41 |
|
|
|
|
|
|
|
| 42 |
```
|
| 43 |
from transformers import pipeline
|
| 44 |
|
|
@@ -69,11 +71,8 @@ Sentiment detection in Polish data (fine-tuned on tweets from political domain).
|
|
| 69 |
It achieves the following results on the test set (10%):
|
| 70 |
|
| 71 |
- No. examples = 100
|
| 72 |
-
|
| 73 |
-
- Batch size = 8
|
| 74 |
-
|
| 75 |
- accuracy = 0.950
|
| 76 |
-
|
| 77 |
- macro f1 = 0.944
|
| 78 |
|
| 79 |
precision recall f1-score support
|
|
|
|
| 39 |
This model is a fine-tuned version of [dkleczek/bert-base-polish-cased-v1](https://huggingface.co/dkleczek/bert-base-polish-cased-v1) to predict 3-categorical sentiment.
|
| 40 |
Fine-tuned on 1k sample of manually annotated Twitter data.
|
| 41 |
|
| 42 |
+
Model developed as a part of ComPathos project: https://www.ncn.gov.pl/sites/default/files/listy-rankingowe/2020-09-30apsv2/streszczenia/497124-en.pdf
|
| 43 |
+
|
| 44 |
```
|
| 45 |
from transformers import pipeline
|
| 46 |
|
|
|
|
| 71 |
It achieves the following results on the test set (10%):
|
| 72 |
|
| 73 |
- No. examples = 100
|
| 74 |
+
- mini batch size = 8
|
|
|
|
|
|
|
| 75 |
- accuracy = 0.950
|
|
|
|
| 76 |
- macro f1 = 0.944
|
| 77 |
|
| 78 |
precision recall f1-score support
|