Demonstrated the basic Information retrieval techniques with python. (tokenization, isolated word correction, context sensitive word correction, Stemming, and Lemmatization)
Data files(available on the repo) of 3 domains are used to demostrate as stated below.
1- Sudent Course Feedback Data 2- Twitter Feed 3- Reseach Papaer
Below Libraries/modules are required as prerequisites
1-installing pyspellchecker as the isolated word corrector
pip install pyspellchecker
2- Installing the symspellpy module pip install -U symspellpy
3- download wordnet lemmarizer >>import nltk >>nltk.download('wordnet')