NLP

Human language is highly ambiguous. People are great at producing language and understanding language, and are capable of expressing, perceiving, and interpreting very elaborate and nuanced meanings. NLP is an ongoing attempt to capture those structures and rules.

At a glance

• In Class Instruction: 4 Hours

  • In Class code along Dataset: Reuter_50_50 Data Set

• Skills Rehearsed

  • Basic usage of the sklearn package

In-Class Activities

• Instructor Monologue
• Introduction to NLP and the NLTK package
• Tokenization, Stopwords, Stemming and Lemmatization, Wordcloud
• Implementations Of NLP Applications
• Bag of words approach using sklearn package
• Model building using TF-IDF vectorizer
• Applications and limitations of the Bag of words approach

Pre Reads

1. Algorithmia's introduction to NLP blog
2. Top 10 NLP terms explained to a newbie
3. Simple introduction to NLP

Slides

Check the Jupyter Notebook in the top right of the screen

Post Reads

1. Guide to understand and implement NLP with Python
2. NLTK book
3. Some tricky sentences for NLP
4. Scaling an NLP problem
5. TF-IDF explained
6. Bag of words model using Python

Project

Check out project ReadME!!