NLP_WSD / README.md
gkc55's picture
Fix NLTK data loading and Docker configuration
24e1f38
metadata
title: Word Sense Disambiguation
emoji: πŸ€–
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false

πŸ‘‹ Hi, I'm Gunjankumar Nitin Choudhari

LinkedIn Portfolio Email YouTube

🎯 About Me

I'm a B.Tech student at Ramrao Adik Institute of Technology, specializing in Computer Engineering with a focus on Data Science. With a strong CGPA of 9.40/10, I'm passionate about building intelligent systems and contributing to technological innovation.

πŸŽ“ Education

  • B.Tech in Computer Engineering (Data Science)
    Ramrao Adik Institute of Technology, D. Y. Patil Deemed to be University
    CGPA: 9.40/10 | 2022 - Present

πŸ› οΈ Tech Stack

  • Languages: Python, Java, C, SQL, NoSQL, HTML, CSS, JavaScript
  • ML/AI: TensorFlow, Scikit-learn, LLMs, Generative AI
  • Web: Flask, JSP, Servlets
  • Mobile: Flutter, Dart
  • Tools: Git, Power BI, VS Code, Jupyter, LaTeX, Figma
  • Cloud: Oracle Cloud, AWS
  • Databases: MySQL, MongoDB

πŸ† Certifications

  • Oracle Cloud Infrastructure 2024 Generative AI Certified Professional
  • Intel Unnati Training on AI
  • Data Science for Engineers (NPTEL)
  • Programming in Python (NPTEL)
  • Alteryx Machine Learning Fundamentals
  • Data Structure and Algorithms – Internshala
  • PowerBI for Beginners - Simplilearn

πŸš€ Featured Projects

1. AgrowAssist

Smart Agricultural Assistance System with ML-powered crop recommendations

  • 35% improved prediction accuracy
  • Flutter mobile app with TensorFlow Lite
  • Real-time disease detection
  • Power BI data visualization

2. AskDB

Natural Language to SQL Query Converter

  • LLM-powered query conversion
  • Flask backend with MySQL integration
  • Responsive Bootstrap UI
  • Efficient API communication

3. LESK BERT WSD

Advanced Word Sense Disambiguation System

  • BERT embeddings integration
  • Enhanced Lesk algorithm
  • Real-time feedback system
  • Flask web interface

πŸ’Ό Professional Experience

Python Data Analyst Intern @ SPRINGBOARD

  • Implemented ML algorithms improving prediction accuracy by 25%
  • Created interactive Power BI dashboards
  • Enhanced data visualization efficiency by 30%

Java Development Trainee @ IT-Networkz Infosystem

  • Developed MVC architecture web applications
  • Optimized database operations with JDBC
  • Improved performance speed by 30%

🎯 Leadership & Activities

  • Head of Design at CSI, RAIT
  • Co-Head Design Officer at CSI, RAIT
  • Co-Chief Design Officer at Social Wing, RAIT
  • NSS Volunteer (2023-2024)
  • Technical Content Creator on YouTube

πŸ“Š GitHub Stats

Your GitHub stats

🌱 Currently Learning

  • Advanced Generative AI
  • Cloud Architecture
  • System Design
  • DevOps practices

🎯 Goals

  • Contribute to open-source projects
  • Master full-stack development
  • Build impactful AI applications
  • Learn cloud technologies

⚑ Fun Fact

When I'm not coding, you'll find me playing football, cricket, or creating graphic designs!


⭐️ From Gunjankumar55

LESK BERT WSD - Advanced Word Sense Disambiguation

Python Flask NLTK BERT

An advanced Word Sense Disambiguation (WSD) system that combines the Lesk algorithm with BERT embeddings for improved accuracy in determining word meanings from context.

πŸš€ Features

  • Enhanced Lesk Algorithm: Improved version of the traditional Lesk algorithm
  • BERT Integration: Uses BERT embeddings for better context understanding
  • Interactive Web Interface: User-friendly Flask-based web application
  • Real-time Feedback System: Learn from user corrections to improve accuracy
  • Context-Aware Processing: Considers surrounding words and phrases
  • Multiple Sense Support: Handles words with multiple meanings effectively

πŸ› οΈ Technical Stack

  • Backend: Flask, Python 3.9
  • NLP: NLTK, BERT Transformers
  • Frontend: HTML, CSS, JavaScript
  • Deployment: Docker, Hugging Face Spaces
  • Version Control: Git

πŸ“‹ Prerequisites

  • Python 3.9+
  • pip (Python package manager)
  • Docker (for containerization)

πŸš€ Quick Start

  1. Clone the repository:
git clone https://github.com/Gunjankumar55/LESK_BERT_WSD.git
cd LESK_BERT_WSD
  1. Install dependencies:
pip install -r requirements.txt
  1. Run the application:
python app.py
  1. Access the web interface at http://localhost:5000

πŸ’‘ Usage

  1. Enter a sentence containing an ambiguous word
  2. The system automatically detects potential ambiguous words
  3. Select a word to disambiguate
  4. View detailed results including:
    • Word definitions
    • Example usage
    • Confidence scores
    • Alternative meanings

🎯 Project Structure

LESK_BERT_WSD/
β”œβ”€β”€ app.py              # Main application file
β”œβ”€β”€ requirements.txt    # Project dependencies
β”œβ”€β”€ Dockerfile         # Docker configuration
β”œβ”€β”€ templates/         # HTML templates
└── static/           # Static assets

🀝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

πŸ“ License

This project is licensed under the MIT License - see the LICENSE file for details.

πŸ‘¨β€πŸ’» Author

Gunjankumar Choudhari

πŸ™ Acknowledgments

  • NLTK team for the excellent NLP tools
  • Hugging Face for BERT implementation
  • Flask team for the web framework