Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,61 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- multilabel-classification
|
| 4 |
+
- emotion-detection
|
| 5 |
+
- text-classification
|
| 6 |
+
- transformers
|
| 7 |
+
- deberta
|
| 8 |
+
- huggingface
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
datasets:
|
| 11 |
+
- custom
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# DeBERTa-v3-Large for Multilabel Emotion Classification
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [`microsoft/deberta-v3-large`](https://huggingface.co/microsoft/deberta-v3-large) for multilabel emotion classification.
|
| 19 |
+
It was trained on a custom dataset where each text sample may contain multiple emotions.
|
| 20 |
+
|
| 21 |
+
## 📌 Model Card
|
| 22 |
+
|
| 23 |
+
- **Model**: `FurqonAryadana/deberta-emotion-multilabel-0.5007`
|
| 24 |
+
- **Base**: DeBERTa-v3-Large
|
| 25 |
+
- **Task**: Multilabel Emotion Classification
|
| 26 |
+
- **License**: Apache 2.0
|
| 27 |
+
- **Language**: English
|
| 28 |
+
- **Threshold Tuning**: Applied per-label
|
| 29 |
+
|
| 30 |
+
## 📊 Evaluation (Validation Set)
|
| 31 |
+
|
| 32 |
+
**Detailed Classification Report (Threshold Tuned)**:
|
| 33 |
+
|
| 34 |
+
| Emotion | Precision | Recall | F1-score | Support |
|
| 35 |
+
|----------------|-----------|--------|----------|---------|
|
| 36 |
+
| amusement | 0.61 | 0.72 | 0.66 | 851 |
|
| 37 |
+
| anger | 0.43 | 0.58 | 0.49 | 999 |
|
| 38 |
+
| annoyance | 0.34 | 0.70 | 0.46 | 1609 |
|
| 39 |
+
| caring | 0.41 | 0.57 | 0.48 | 594 |
|
| 40 |
+
| confusion | 0.49 | 0.71 | 0.58 | 800 |
|
| 41 |
+
| disappointment | 0.30 | 0.47 | 0.37 | 990 |
|
| 42 |
+
| disgust | 0.27 | 0.49 | 0.35 | 584 |
|
| 43 |
+
| embarrassment | 0.33 | 0.32 | 0.33 | 308 |
|
| 44 |
+
| excitement | 0.45 | 0.47 | 0.46 | 632 |
|
| 45 |
+
| fear | 0.49 | 0.54 | 0.52 | 321 |
|
| 46 |
+
| gratitude | 0.83 | 0.73 | 0.78 | 955 |
|
| 47 |
+
| joy | 0.43 | 0.58 | 0.50 | 876 |
|
| 48 |
+
| love | 0.64 | 0.79 | 0.71 | 701 |
|
| 49 |
+
| sadness | 0.40 | 0.57 | 0.47 | 714 |
|
| 50 |
+
|
| 51 |
+
- **F1 Micro**: `0.5101`
|
| 52 |
+
- **F1 Macro**: `0.5107`
|
| 53 |
+
|
| 54 |
+
## 🧠 Emotions (Label Order)
|
| 55 |
+
|
| 56 |
+
```python
|
| 57 |
+
[
|
| 58 |
+
'amusement', 'anger', 'annoyance', 'caring', 'confusion', 'disappointment',
|
| 59 |
+
'disgust', 'embarrassment', 'excitement', 'fear', 'gratitude', 'joy',
|
| 60 |
+
'love', 'sadness'
|
| 61 |
+
]
|