This project implements a simple text summarizer using the Flask web framework. The summarization process is based on TF-IDF (Term Frequency-Inverse Document Frequency). Users can input text through a web interface, and the application generates a summary based on the provided input.
Project Structure β’ app.py: The main file that contains the Flask application. β’ CORE/text_summarizer.py: The module with the function for text summarization. β’ templates/index.html: The HTML template for the web interface.
Dependencies
β’ Flask: A micro web framework for Python.
β’ NLTK: A natural language processing library.
β’ scikit-learn: A machine learning library for Python.
Features π
TF-IDF Calculation π
The core functionality of the project revolves around calculating TF-IDF scores for words in the input text. TF-IDF scores help identify the significance of each word in the context of the entire document corpus.
Sentence Extraction π Using TF-IDF scores, the system extracts the most important sentences from the original text. These sentences encapsulate the essential information and contribute to the final summary. Installation
- Install the required Python packages: bashCopy code pip install Flask nltk scikit-learn
- Download NLTK data: pythonCopy code import nltk nltk.download('punkt') nltk.download('stopwords')
- Run the Flask application: bashCopy code python app.py
- Access the web interface at http://localhost:5000 in your browser. Usage
- Enter the text you want to summarize in the provided textarea.
- Optionally, specify the number of sentences for the summary.
- Click the "Summarize" button.
- View the original text and the generated summary.
β’ This project uses a TF-IDF-based extractive summarization approach.
β’ The summarization function is located in the CORE/text_summarizer.py file.
β’ Adjust the parameters in the tfidf_summarize function for desired summarization length.
β’ Explore more advanced summarization methods, such as BERT-based models.
β’ Enhance the user interface with additional features.
