Skip to content

CodeWithDK1511/Summer-intern

Repository files navigation

NLP Internship Projects

This repository contains my work completed during a summer internship, focused on Natural Language Processing (NLP) and transformer-based models for sentiment analysis.

📌 Overview

The primary goal of this project is to explore and implement modern NLP techniques using deep learning models such as BERT, RoBERTa, and DeBERTa for sentiment classification tasks, including Hindi text sentiment analysis.


📂 Repository Structure

Summer_intern/
│
├── Bert_model.ipynb              # BERT implementation
├── Roberta_model.ipynb          # RoBERTa implementation
├── Deberta_model_1.ipynb        # DeBERTa implementation
├── sentiment_analysis.ipynb     # General sentiment analysis pipeline
├── hindi_text_sentiment.csv     # Dataset used
├── Summer_Internship_Presentation.pptx  # Final presentation
└── freeglut-MinGW-3.0.0-1.mp/   # Supporting files

🚀 Models Used

  • BERT (Bidirectional Encoder Representations from Transformers)
  • RoBERTa (Robustly Optimized BERT Approach)
  • DeBERTa (Decoding-enhanced BERT with disentangled attention)

These models were fine-tuned for sentiment classification tasks.


🧠 Key Features

  • Implementation of transformer-based models for NLP tasks
  • Sentiment analysis on Hindi text dataset
  • Comparative experimentation with multiple architectures
  • Data preprocessing and model evaluation

🛠️ Technologies Used

  • Python
  • Jupyter Notebook
  • PyTorch / Transformers (Hugging Face)
  • Pandas, NumPy, Scikit-learn

📊 Dataset

The dataset used:

  • hindi_text_sentiment.csv
  • Contains labeled Hindi text for sentiment classification

▶️ How to Run

  1. Clone the repository:
git clone https://github.com/your-username/your-repo-name.git
  1. Navigate to the folder:
cd Summer_intern
  1. Open Jupyter Notebook:
jupyter notebook
  1. Run any .ipynb file step by step

📈 Results

  • Successfully implemented multiple transformer models
  • Observed performance differences across architectures
  • Built a working sentiment classification pipeline

📎 Future Improvements


About

No description or website provided.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors