Natural Language Processing – Basic to Advance using Python

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction and Walk through of contents

Lecture 2: Presentation ppt and Python code

Lecture 3: Installations and Technology

Lecture 4: Various Libraries

Lecture 5: What Is Natural Language Processing

Lecture 6: Applications of NLP

Chapter 2: Basic

Lecture 1: Basic string operations

Lecture 2: Basic regex

Lecture 3: NLTK Install and Testing

Lecture 4: NLTK Tokenizers

Lecture 5: NLTK Part-of-speech tagging

Lecture 6: NLTK Stemming and Lemmatization

Lecture 7: NLTK Word-sense disambiguation

Lecture 8: NLTK BLEU Scores

Lecture 9: Stanford NLP

Lecture 10: TextBlob

Lecture 11: Miscellaneous

Lecture 12: String Cleaning part1

Lecture 13: String Cleaning part2

Lecture 14: String Cleaning part3

Lecture 15: String Cleaning part4

Lecture 16: WordCloud

Chapter 3: Intermediate

Lecture 1: Overall approach for NLP solutions

Lecture 2: Entity resolution or Deduplication

Lecture 3: Entity resolution or Deduplication – data prep

Lecture 4: Entity resolution or Deduplication – single table

Lecture 5: Entity resolution or Deduplication – two tables

Lecture 6: Text to Features – One hot encoding

Lecture 7: Count vectorizer

Lecture 8: TF-IDF (Term Frequency, Inverse Document Frequency)

Lecture 9: Word embedding

Lecture 10: Word2vec and GloVe

Lecture 11: Word embedding of custom review data

Lecture 12: Word Sense Disambiguation

Lecture 13: Speech Recognition using Microphone

Lecture 14: Speech Recognition using Audio Files

Lecture 15: Similarity between two strings

Lecture 16: Language Translation

Lecture 17: Computational Linguistics

Lecture 18: Computational Linguistics – Dependency Extraction

Chapter 4: Advance

Lecture 1: Advance – Introductions

Lecture 2: Classifications using Random Forest

Lecture 3: Classifications using Naive Bayes and XgBoost

Lecture 4: Classifications using DL with tfkeras MLP

Lecture 5: Classifications using DL with tfkeras inbuilt embedded layer

Lecture 6: Classifications using DL with tfkeras WordVector transformed to average

Lecture 7: Classifications using DL with tfkeras custom WordVector

Lecture 8: How to know models are good enough Bias vs Variance

Lecture 9: Sentiment analysis

Lecture 10: K-means clustering

Lecture 11: Topic modeling

Lecture 12: Search engine

Lecture 13: Miscellaneous