Instructions to use chkla/roberta-argument with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chkla/roberta-argument with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="chkla/roberta-argument")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("chkla/roberta-argument") model = AutoModelForSequenceClassification.from_pretrained("chkla/roberta-argument", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,19 +1,19 @@
|
|
| 1 |
Welcome to **RoBERTArg**!
|
| 2 |
|
| 3 |
-
π€ **
|
| 4 |
|
| 5 |
-
π· Using **
|
| 6 |
|
| 7 |
-
π **
|
| 8 |
| Model | Acc | F1 | R arg | R non | P arg | P non |
|
| 9 |
|----|----|----|----|----|----|----|
|
| 10 |
| robertArg | 0.80577 | 0.78407| 0.8147 | 0.7989 | 0.7557 | 0.8496 |
|
| 11 |
|
| 12 |
-
**
|
| 13 |
-
| | **
|
| 14 |
|----|----|----|
|
| 15 |
-
| **
|
| 16 |
-
| **
|
| 17 |
|
| 18 |
ππΎ Check out _chkla/argument-analyzer/_ for more details.
|
| 19 |
|
|
|
|
| 1 |
Welcome to **RoBERTArg**!
|
| 2 |
|
| 3 |
+
π€ **Training**: Model (RoBERTA_base_) fine-tuned on a heterogeneous argument corpus (~40K sentences, Stab et al. (2018) π) corpus of several controversial topics (abortion etc.).
|
| 4 |
|
| 5 |
+
π· Using **NON-ARGUMENT** (0) and **ARGUMENT** (1) as labels.
|
| 6 |
|
| 7 |
+
π **Performance**
|
| 8 |
| Model | Acc | F1 | R arg | R non | P arg | P non |
|
| 9 |
|----|----|----|----|----|----|----|
|
| 10 |
| robertArg | 0.80577 | 0.78407| 0.8147 | 0.7989 | 0.7557 | 0.8496 |
|
| 11 |
|
| 12 |
+
**Confusion Matrix**
|
| 13 |
+
| | **1** | **0** |
|
| 14 |
|----|----|----|
|
| 15 |
+
| **1** | 2214 | 557 |
|
| 16 |
+
| **0** | 392 | 1723 |
|
| 17 |
|
| 18 |
ππΎ Check out _chkla/argument-analyzer/_ for more details.
|
| 19 |
|