This repository contains the code which can generate extractive summary of medical transcription documents
- numpy
- scipy
- nltk
- scikit-learn
- pattern
- pyteaser
- sumy
numpy: $ sudo pip install numpy
nltk: $ sudo pip install nltk
scipy: $ sudo pip install scipy
scikit-learn: $ sudo pip install sklearn
pattern: $ sudo pip install pattern
pyteasaer: $ sudo pip install pyteaser
summy: $ sudo pip install sumy
-
For running base-line approach run the
pyteaser_demo.py
andsumy_demo.py
files which are put inside the Base_line_approach folder -
For running revised approach run the
summarize.py
file which is put inside the Revised_approach folder -
For running best approach run the
document_summarization.py
file which is put inside Best_approach folder
Code credits for this code go to dipanjanS, Xiao and Tristan Havelick. I've merely created a wrapper and necessary changes to get people started.