KPMG-Challenge

Text Summarizer for KIC 2020

Contributors:

• Me for developing NLP core function
• Nguyen Ngoc Phat for developing website

Running the code

Libraries

Please make sure that you have the following libraries installed in your system-

• numpy
• matplotlib
• networkx
• nltk
• sklearn
• PyPDF2
• pymupdf
• fpdf

You may be confused with 3 packages for handling PDF file. All 3 are for PDF but for different purposes:

• PyPDF2: is consider to the easiest way to read PDF
• pymupdf: is the only way to highlight annotation in PDF
• fpdf: can be replaced with pymupdf for write PDF from blank