Roberta Fact Check

🚀 Roberta-Fact-Check Model

The Roberta-Fact-Check Model is a deep - learning solution for text classification. It leverages the Roberta architecture to determine whether a claim is supported or refuted by the provided evidence.

🚀 Quick Start

The Roberta-Fact-Check Model is straightforward to use. Just input a claim and its corresponding evidence, and it will output a label indicating the relationship between the claim and the evidence. This model can be easily integrated into various applications for fact - checking and misinformation detection.

✨ Features

• Utilizes the Roberta architecture for text classification.
• Classifies claims as either supported or refuted based on evidence.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

import torch
from transformers import RobertaTokenizer, RobertaForSequenceClassification

# Load the tokenizer and model
tokenizer = RobertaTokenizer.from_pretrained('Dzeniks/roberta-fact-check')
model = RobertaForSequenceClassification.from_pretrained('Dzeniks/roberta-fact-check')

# Define the claim with evidence to classify
claim = "Albert Einstein work in the field of computer science"
evidence = "Albert Einstein was a German-born theoretical physicist, widely acknowledged to be one of the greatest and most influential physicists of all time."

# Tokenize the claim with evidence
x = tokenizer.encode_plus(claim, evidence, return_tensors="pt")

model.eval()
with torch.no_grad():
  prediction = model(**x)

label = torch.argmax(prediction[0]).item()

print(f"Label: {label}")

📚 Documentation

Model Training

The model was trained using the Adam optimizer. The hyperparameters were set as follows: a learning rate of 2 - 4e, an epsilon of 1 - 8, and a weight decay of 2 - 8e. The training dataset primarily included the FEVER and Hover datasets, along with a small amount of manually created data.

Input and Output

The model takes a claim and corresponding evidence as input. It returns a label indicating whether the evidence supports or refutes the claim. The two possible labels are:

• 0: Supports
• 1: Refutes

🔧 Technical Details

The model uses the Roberta architecture for text classification. It is trained on a combination of well - known datasets (FEVER and Hover) and some manually created data. The Adam optimizer is used with specific hyperparameters to fine - tune the model.

📄 License

This project is licensed under the MIT license.

Acknowledgements

This model was developed using the Hugging Face transformers library and trained on the FEVER and Hover datasets. We appreciate the developers of these datasets for their contributions to the community.

Disclaimer

Although the Roberta - Fact - Check Model has been trained on a large dataset and can offer accurate results in many scenarios, it may not always yield correct outcomes. Users should exercise caution when making decisions based on the output of any machine learning model.