Question Answering Model Finetuned On Bert

🚀 Question Answering Bot

This project implements an interactive Question Answering Bot using a fine - tuned BERT model. It can take context and questions as input and return answers. The Gradio interface enables user - friendly interaction.

🚀 Quick Start

To run the Question Answering Bot, you need to have the required libraries installed, including Gradio and Transformers.

Running the Gradio App

You can find the Gradio app code in the file gradio_app.py. To launch the app, simply run:

$ python gradio_app.py

Using the Notebook

The complete code, including model training and the Gradio app, is available in the Jupyter Notebook QuestionAnsweringBot.ipynb. You can run it using Jupyter to explore and modify the code as needed.

⚠️ Important Note

It is recommended to run this notebook on paperspace.com for no errors as when I ran this on Google Colab it was showing some import errors which I was unable to resolve.

✨ Features

• The bot uses a pre - trained BERT model fine - tuned on the SQuAD dataset, enabling it to answer questions based on given context.
• It includes a Gradio interface, allowing users to interact with the model through a user - friendly web application.
• Users can provide the context by either manually entering it or by uploading a text file. The interface also has options to remember the context for subsequent questions and clear it when needed.

📦 Installation

To run this project, you need to install the required libraries such as Gradio and Transformers. However, specific installation commands are not provided in the original README.

💻 Usage Examples

Basic Usage

The basic usage is to run the Gradio app:

$ python gradio_app.py

Advanced Usage

You can explore and modify the code in the Jupyter Notebook QuestionAnsweringBot.ipynb to customize the model training and usage.

📚 Documentation

Model

The model used in this project is based on BERT (Bidirectional Encoder Representations from Transformers), a state - of - the - art NLP model. Specifically, we use the "Graphcore/bert - large - uncased" variant, optimized for question answering tasks.

Task

The primary task of this bot is to answer questions based on a given context.

Dataset

The model was fine - tuned using the SQuAD dataset, which is a collection of questions and answers based on Wikipedia articles. This dataset provides a rigorous benchmark for evaluating the model's question - answering abilities.

🔧 Technical Details

The major challenge faced during this project was the implementation of IPU as it was pretty complex. The author was unable to run it on either their laptop or on Google Colab and had to take a lot of help from Google and ChatGPT. After finally implementing it, there was a sense of accomplishment.

📄 License

No license information is provided in the original README.