|
--- |
|
license: mit |
|
datasets: |
|
- SkyWater21/lv_go_emotions |
|
language: |
|
- lv |
|
--- |
|
Fine-tuned [LVBERT](https://huggingface.co/AiLab-IMCS-UL/lvbert) for multi-label emotion classification task. |
|
|
|
Model was trained on [lv_go_emotions](https://huggingface.co/datasets/SkyWater21/lv_go_emotions) dataset. This dataset is Latvian translation of [GoEmotions](https://huggingface.co/datasets/go_emotions) dataset. Google Translate was used to generate the machine translation. |
|
|
|
Original 26 emotions were mapped to 6 base emotions as per Dr. Ekman theory. |
|
|
|
Labels predicted by classifier: |
|
```yaml |
|
0: anger |
|
1: disgust |
|
2: fear |
|
3: joy |
|
4: sadness |
|
5: surprise |
|
6: neutral |
|
``` |
|
|
|
Label mapping from 27 emotions from GoEmotion to 6 base emotions as per Dr. Ekman theory: |
|
|GoEmotion|Ekman| |
|
|---|---| |
|
| admiration | joy| |
|
| amusement | joy| |
|
| anger | anger| |
|
| annoyance | anger| |
|
| approval | joy| |
|
| caring | joy| |
|
| confusion | surprise| |
|
| curiosity | surprise| |
|
| desire | joy| |
|
| disappointment | sadness| |
|
| disapproval | anger| |
|
| disgust | disgust| |
|
| embarrassment | sadness| |
|
| excitement | joy| |
|
| fear | fear| |
|
| gratitude | joy| |
|
| grief | sadness| |
|
| joy | joy| |
|
| love | joy| |
|
| nervousness | fear| |
|
| optimism | joy| |
|
| pride | joy| |
|
| realization | surprise| |
|
| relief | joy| |
|
| remorse | sadness| |
|
| sadness | sadness| |
|
| surprise | surprise| |
|
| neutral | neutral| |
|
|
|
Seed used for random number generator is 42: |
|
```python |
|
def set_seed(seed=42): |
|
random.seed(seed) |
|
np.random.seed(seed) |
|
torch.manual_seed(seed) |
|
if torch.cuda.is_available(): |
|
torch.cuda.manual_seed_all(seed) |
|
``` |
|
|
|
Training parameters: |
|
```yaml |
|
max_length: null |
|
batch_size: 32 |
|
shuffle: True |
|
num_workers: 2 |
|
pin_memory: False |
|
drop_last: False |
|
|
|
optimizer: adam |
|
lr: 0.00001 |
|
weight_decay: 0 |
|
|
|
problem_type: multi_label_classification |
|
|
|
num_epochs: 3 |
|
``` |
|
|
|
|
|
Evaluation results on test split of [lv_go_emotions](https://huggingface.co/datasets/SkyWater21/lv_go_emotions/viewer/simplified_ekman) |
|
| |Precision|Recall|F1-Score|AUC-ROC|Support| |
|
|--------------|---------|------|--------|-------|-------| |
|
|anger | 0.57| 0.40| 0.47| 0.85| 726| |
|
|disgust | 0.64| 0.28| 0.39| 0.93| 123| |
|
|fear | 0.63| 0.54| 0.58| 0.95| 98| |
|
|joy | 0.80| 0.79| 0.79| 0.91| 2104| |
|
|sadness | 0.70| 0.44| 0.54| 0.90| 379| |
|
|surprise | 0.63| 0.44| 0.52| 0.89| 677| |
|
|neutral | 0.65| 0.62| 0.64| 0.83| 1787| |
|
|micro avg | 0.70| 0.61| 0.66| 0.93| 5894| |
|
|macro avg | 0.66| 0.50| 0.56| 0.89| 5894| |
|
|weighted avg | 0.69| 0.61| 0.65| 0.88| 5894| |
|
|samples avg | 0.65| 0.63| 0.63| nan| 5894| |
