NLPDash

Advanced NLP Toolkit

A powerful Natural Language Processing web application built with Streamlit and Stanza

Perform Part-of-Speech tagging, Named Entity Recognition, Dependency Parsing, and Lemmatization with interactive visualizations.

What the project includes

Core NLP Capabilities

** Part-of-Speech Tagging** - Identify nouns, verbs, adjectives, and more
** Named Entity Recognition** - Extract people, organizations, locations, dates
** Dependency Parsing** - Analyze grammatical relationships
** Lemmatization** - Convert words to their base forms
** Interactive Visualizations** - Beautiful charts and color-coded tags

Multiple Input Methods

** Text Input** - Type or paste text directly
** Voice Recording** - Transcribe speech to text (optional)
** File Upload** - Process .txt and .md files

User Experience

** Dark Theme** - Optimized for comfortable viewing
** Statistics Dashboard** - Word counts, sentence analysis, entity statistics
** Export Results** - Download POS tags and entities as CSV
** Configurable Options** - Enable/disable features as needed

Quick Start

Prerequisites

Python 3.8 or higher
pip package manager

Installation

Clone the repository

git clone https://github.com/Tuhin-SnapD/NLPDash.git
cd NLPDash

Install dependencies
```
pip install -r requirements.txt
```
Run the application
```
streamlit run app.py
```
Open your browser
- Navigate to http://localhost:8501
- Start analyzing text!

First Launch

On first run, Stanza will automatically download the English model (~500MB). This happens once and may take a few minutes. Subsequent launches will be much faster!

Usage Guide

Basic Usage

Enter Your Text
- Select "Text" input mode
- Type or paste your text in the text area
- Click " Analyze Text"
View Results
- POS Tagging Tab: See parts of speech with color-coded tags
- Named Entities Tab: View detected entities and their types
- Dependencies Tab: Explore grammatical relationships
- Statistics Tab: Review comprehensive text statistics
Customize Analysis
- Toggle features in the sidebar (NER, Dependency Parsing, Lemmatization)
- Adjust display options (tables, charts, colored tags)
- Show or hide lemmas in tags

Advanced workflows

Voice Recording

# Requires SpeechRecognition and PyAudio
pip install SpeechRecognition pyaudio

Click " Record from Microphone"
Speak clearly for best results
Uses Google's speech recognition API

File Upload

Select "File Upload" mode
Upload .txt or .md files
Edit the loaded content if needed
Analyze as normal

Export Results

Click " Download POS Tags CSV" for tagging results
Click " Download Entities CSV" for named entities
Both files are UTF-8 encoded and ready for analysis

Example Use Cases

News Article Analysis

Input: "Apple Inc. was founded by Steve Jobs in Cupertino, California."
Results:
- Named Entities: Apple Inc. (ORG), Steve Jobs (PERSON), Cupertino (GPE)
- POS Tags: Noun, Verb, Preposition, etc.
- Dependencies: Subject-Verb-Object relationships

Academic Text Processing

Input: "Machine learning algorithms use neural networks to process data."
Results:
- Technical terminology identified
- POS tags for each word
- Dependency tree visualization

Business Document Analysis

Input: Financial reports, contracts, or business documents
Results:
- Named entities (companies, amounts, dates)
- Statistical analysis
- Export to CSV for further processing

How the system is built

Tech Stack

Component	Technology	Purpose
Web Framework	Streamlit	Interactive web interface
NLP Engine	Stanza	State-of-the-art NLP processing
Visualization	Plotly	Interactive charts
Data Processing	Pandas	Data manipulation and export
Speech Recognition	SpeechRecognition	Voice-to-text transcription

Pipeline

Input Text → Stanza Pipeline → Processing → Results
                ↓
         [Tokenization]
         [POS Tagging]
         [Lemmatization]
         [NER]
         [Dependency Parsing]
                ↓
         Interactive Display
         [Tables, Charts, HTML]
         [Export Options]

Sample Outputs

POS Tagging

Color-coded tags for each part of speech
Tables with UPOS and XPOS tags
Distribution charts showing tag frequencies

Named Entities

Highlighted entities in text with type labels
Entity type distribution charts
Exportable data with start/end positions

Dependency Parsing

Dependency relations table
Top relations visualization
Grammatical structure analysis

Configuration

Requirements

streamlit>=1.28.0
stanza>=1.6.0
pandas>=2.0.0
SpeechRecognition>=3.10.0
plotly>=5.17.0
pytest>=8.0.0

Optional Dependencies

# For voice recording
pip install SpeechRecognition pyaudio

Streamlit Configuration

See .streamlit/config.toml for customization:

[theme]
primaryColor = "#1976D2"
backgroundColor = "#0E1117"
secondaryBackgroundColor = "#262730"
textColor = "#FAFAFA"

[server]
headless = true

Troubleshooting

Common Issues

Issue: Stanza model download fails

# Solution: Download manually
python -c "import stanza; stanza.download('en')"

Issue: Speech recognition not working

# Check PyAudio installation
pip install pyaudio

# On Windows, may need:
# pip install pipwin
# pipwin install pyaudio

Issue: Port already in use

# Use different port
streamlit run app.py --server.port 8502

Issue: Memory errors with large texts

Split text into smaller chunks
Process paragraph by paragraph
Consider using batch processing for very large files

Performance

Model Loading: ~2-3 seconds (first time)
Text Processing: ~100-200 tokens/second
Memory Usage: ~500MB-1GB (depends on text size)
UI Response: Real-time for typical documents

Optimizations

Cached Stanza pipeline (Streamlit @cache_resource)
Efficient pandas DataFrame operations
Lazy loading of visualizations
Optimized HTML rendering

Contributing

Contributions are welcome! Here's how you can help:

Fork the repository

Create a feature branch

git checkout -b feature/amazing-feature

Commit your changes
```
git commit -m "Add amazing feature"
```

Push to the branch

git push origin feature/amazing-feature

Open a Pull Request

Development Setup

# Clone repository
git clone https://github.com/Tuhin-SnapD/NLPDash.git
cd NLPDash

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Install development dependencies
pip install pytest pytest-cov black flake8

# Run tests
pytest

# Format code
black app.py

# Lint code
flake8 app.py

License

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

Acknowledgments

Stanza - Stanford NLP Group for the powerful NLP library
Streamlit - For the amazing web framework
Plotly - For beautiful interactive visualizations
SpeechRecognition - For voice transcription capabilities

Contact

Project Maintainer: Tuhin SnapD
GitHub: @Tuhin-SnapD

Future Enhancements

Star History

If you find this project helpful, please consider giving it a star! ⭐

Built with using Streamlit, Stanza, and Python

⬆ Back to Top