Text Classification
Transformers
PyTorch
Safetensors
English
roberta
uncertainty-detection
social-media
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("ChrisLiewJY/BERTweet-Hedge")
model = AutoModelForSequenceClassification.from_pretrained("ChrisLiewJY/BERTweet-Hedge")Quick Links
Overview
Fine tuned VinAI's BERTweet base model on the Wiki Weasel 2.0 Corpus from the Szeged Uncertainty Corpus for hedge (linguistic uncertainty) detection in social media texts. Model was trained and optimised using Ray Tune's implementation of Deep Mind's Population Based Training with the arithmetic mean of Accuracy & F1 as its evaluation metric.
Labels
- LABEL_1 = Positive (Hedge is detected within text)
- LABEL_0 = Negative (No Hedges detected within text)
Model Performance
| Model | Accuracy | F1-Score | Accuracy & F1-Score |
|---|---|---|---|
BERTweet-Hedge |
0.9680 | 0.8765 | 0.9222 |
- Downloads last month
- 721
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ChrisLiewJY/BERTweet-Hedge")