Boolq T5 Base Question Generation

🚀 BoolQ T5

This repository hosts a fine - tuned T5 - base model on the BoolQ dataset, enabling the generation of true/false question - answer pairs. It leverages T5's text - to - text framework to generate natural language questions and corresponding yes/no answers from a given passage.

🚀 Quick Start

You can easily utilize this model for inference using the Hugging Face Transformers pipeline:

from transformers import pipeline

generator = pipeline("text2text-generation", model="Fares7elsadek/boolq-t5-base-question-generation")

# Example inference:
input_text = "truefalse: [answer] passage: [Your passage here] </s>"
result = generator(input_text)
print(result)

✨ Features

• Built with PyTorch Lightning, it streamlines training, validation, and hyperparameter tuning.
• Adapts the pre - trained T5 - base model to question generation and answer prediction, bridging comprehension and generation in a single framework.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

from transformers import pipeline

generator = pipeline("text2text-generation", model="Fares7elsadek/boolq-t5-base-question-generation")

# Example inference:
input_text = "truefalse: [answer] passage: [Your passage here] </s>"
result = generator(input_text)
print(result)

📚 Documentation

Model Overview

Built with PyTorch Lightning, this implementation streamlines training, validation, and hyperparameter tuning. By adapting the pre - trained T5 - base model to the task of question generation and answer prediction, it effectively bridges comprehension and generation in a single framework.

Data Processing

Input Construction

Each input sample is formatted as follows:

truefalse: [answer] passage: [passage] </s>

Target Construction

Each target sample is formatted as:

question: [question] answer: [yes/no] </s>

The boolean answer is normalized to “yes” or “no” to ensure consistency during training.

Training Details

• Framework: PyTorch Lightning
• Optimizer: AdamW with linear learning rate scheduling and warmup
• Batch Sizes:
  • Training: 6
  • Evaluation: 6
• Maximum Sequence Length: 256 tokens
• Number of Training Epochs: 4

Evaluation Metrics

The model’s performance was evaluated using BLEU scores for both the generated questions and answers. For question generation, the metrics are as follows:

Note: These metrics offer a quantitative assessment of the model’s quality in generating coherent and relevant question - answer pairs.

🔧 Technical Details

The model uses a pre - trained T5 - base model and fine - tunes it on the BoolQ dataset. The data processing steps ensure that the input and target samples are in a proper format for training. The training is carried out using PyTorch Lightning with specific optimizers and hyperparameters.

📄 License

This project is licensed under the MIT license.