Getting an Idea of NLP and its Applications
  • Note!
  • Introduction to NLP
  • By The End Of This Section
  • Installation
  • Tips
  • U - Tokenization
  • P - Tokenization
  • U - Stemming
  • P - Stemming
  • U - Lemmatization
  • P - Lemmatization
  • U - Chunks
  • P - Chunks
  • U - Bag Of Words
  • P - Bag Of Words
  • U - Category Predictor
  • P - Category Predictor
  • U - Gender Identifier
  • P - Gender Identifier
  • U - Sentiment Analyzer
  • P - Sentiment Analyzer
  • U - Topic Modeling
  • P - Topic Modeling
  • Summary
Feature Engineering
  • Using Google Colab
  • Introduction
  • One Hot Encoding
  • Count Vectorizer
  • N-grams
  • Hash Vectorizing
  • Word Embedding
  • FastText
Dealing with corpus and WordNet
  • Introduction
  • In-built corpora
  • External Corpora
  • Corpuses & Frequency Distribution
  • Frequency Distribution
  • WordNet
  • Wordnet with Hyponyms and Hypernyms
  • The Average according to WordNet
Create your Vocabulary for any NLP Model
  • Putting the previous knowledge together
  • Introduction and Challenges
  • 1 - Building your Vocabulary
  • 2 - Building your Vocabulary
  • 3 - Building your Vocabulary
  • 4 - Building your Vocabulary
  • 5 - Building your Vocabulary
  • Dot Product
  • Similarity using Dot Product
  • Reducing Dimensions of your Vocabulary using token improvement
  • Reducing Dimensions of your Vocabulary using n-grams
  • Reducing Dimensions of your Vocabulary using normalizing
  • Reducing Dimensions of your Vocabulary using case normalization
  • When to use stemming and lemmatization?
  • Sentiment Analysis Overview
  • Two approaches for sentiment analysis
  • Sentiment Analysis using rule-based
  • Sentiment Analysis using machine learning - 1
  • Sentiment Analysis using machine learning - 2
  • Summary
Word2Vec in Detail and what is going on under the hood
  • Introduction
  • Bag of words in detail
  • Vectorizing
  • Vectorizing and Cosine Similarity
  • Topic modeling in Detail
  • Make your Vectors will more reflect the Meaning, or Topic, of the Document
  • Sklearn in a short way
  • Summary
Find and Represent the Meaning or Topic of Natural Language Text
  • Note!
  • Keyword Search VS Semantic Search
  • Problems in TI-IDF leads to Semantic Search
  • Transform TF-IDF Vectors to Topic Vectors under the hood