Natural Language Processing from Scratch - Bag of Words Model for Text Classification

Enroll in the course: https://zerotonlp.com
Join Slack community: https://bit.ly/jovian-slack-community

Code & resources: https://jovian.ai/learn/nautral-langu...

Natural Language Processing is the branch of Computer Science that deals with understanding, analyzing, and generating human language e.g. English, Hindi, French, etc. In this series, we will cover the foundational concepts of Natural Language Processing from scratch.

Topics Covered
00:00:00 - Introduction & Code Execution
00:12:56 - 1. Data Download & Exploration
00:36:02 - 2. Text Preprocessing Techniques
01:02:17 - 3. Bag of Words Implementation
01:24:28 - 4. ML Models for Text Classification
01:49:24 - 5. (Bonus) Submit Predictions to Kaggle
02:06:45 - Summary & Future Work

Resources:
Quora Insincere Question Classification competition: https://www.kaggle.com/c/quora-insinc...
Download Kaggle datasets in Jupyter notebooks: https://jovian.ai/himani007/kaggle-op...
Precision, Recall and F1 score: https://towardsdatascience.com/accura...
What is NLP: https://www.ibm.com/cloud/learn/natur...
Text preprocessing with NLTK: https://realpython.com/nltk-nlp-python/
CountVectorizer documentation: https://scikit-learn.org/stable/modul...
LogisticRegression documentation: https://scikit-learn.org/stable/modul...
Data Analysis with Python: https://zerotopandas.com
Machine Learning with Python: https://zerotogbms.com
Open Datasets Library: https://github.com/JovianML/opendatasets

Are you looking to start a career in Data Science? Sign up for our 6-month Data Science & Machine Learning Bootcamp here: https://www.jovian.ai