NLP-Natural Language Processing in Python for Beginners

1. Introduction to the Course

This video provides an overview of the entire course.

2. Introduction to the Instructor

This video provides an introduction to the instructor.

3. Introduction to the Co-Instructor

In this video, you will be introduced to the co-instructor.

4. Course Introduction

This video introduces you to the course.

1. What is Regular Expression

This video introduces us to the concept of regular expression.

2. Why Regular Expression

in this session, we will understand why regular expressions are used.

3. ELIZA Chatbot

In this lesson, we will discuss about Eliza chatbot.

4. Python Regular Expression Package

Let's understand the Python regular expression package in detail.

1. Metacharacters

Let's get introduced to metacharacters in this lesson.

2. Metacharacters Bigbrackets Exercise

In this lesson, we will learn about the square brackets metacharacter.

3. Meta Characters Bigbrackets Exercise Solution

In the previous lesson, we saw a problem; in this lesson, we will work on the solution together.

4. Metacharacters Bigbrackets Exercise 2

Let's take a look at another problem and find out the solution.

5. Metacharacters Bigbrackets Exercise 2 - Solution

Let's find out the solution to the problem we saw in the previous session.

6. Metacharacters Cap

In this lesson, we will learn about the Cap (^) metacharacter.

7. Metacharacters Cap Exercise 3

Now that we are familiar with square brackets and cap metacharacter, it's time to solve a problem period.

8. Metacharacters Cap Exercise 3 - Solution

Let's look at the solution of the problem we discussed in the previous lesson.

9. Backslash

In this session, we will learn about the backslash metacharacter.

10. Backslash Continued

Let's explore more about the backslash metacharacter.

11. Backslash Continued - 01

We will continue our discussion on the backslash metacharacter in this session as well.

12. Backslash Squared Brackets Exercise

It's exercise time; let's take a look at a problem.

13. Backslash Squared Brackets Exercise Solution

Let's find out the solution to the problem we discussed in the previous lesson.

14. Backslash Squared Brackets Exercise - Another Solution

Let's look at another solution to the same problem period.

15. Backslash Exercise

In this session, we will see another practice problem period and understand the problem question first.

16. Backslash Exercise Solution and Special Sequences Exercise

In this session, we will solve the problem we discussed in the previous video.

17. Solution and Special Sequences Exercise Solution

In this session, we will look at an exercise on special sequences for pattern matching.

18. Metacharacter Asterisk

In this session, we will learn about the asterisk metacharacter.

19. Metacharacter Asterisk Exercise

Let's look at an exercise on the asterisk metacharacter.

20. Metacharacter Asterisk Exercise Solution

Let's find the solution to the exercise we discussed in the previous video session.

21. Metacharacter Asterisk Homework

Here is a problem you can solve by yourself (homework).

22. Metacharacter Asterisk Greedy Matching

In this session, we will discuss about an important concept called greedy matching.

23. Metacharacter Plus and Question Mark

In this session, we will learn about the Plus and Question mark metacharacters.

24. Metacharacter Curly Brackets Exercise

Let's discuss about the metacharacter curly brackets in this session.

25. Metacharacter Curly Brackets Exercise Solution

Let's look at the solution for the problem we discussed in the previous video.

1. Pattern Objects

In this session, we will learn about pattern objects.

2. Pattern Objects Match Method Exercise

In this session, we will discuss about two specific methods of pattern objects, which are match() and search().

3. Pattern Objects Match Method Exercise Solution

Let's find the solution to the problem we discussed in the previous video.

4. Pattern Objects Match Method Versus Search Method

Let's understand the difference between match() and search() methods in this session.

5. Pattern Objects Finditer Method

In this lesson, we will look at the finditer built-in function.

6. Pattern Objects Finditer Method Exercise Solution

Let's look at the solution to the problem we discussed in the previous video lesson.

1. Metacharacters Logical Or

In this lesson, we will learn about the logical or metacharacter.

2. Metacharacters Beginning and End Patterns

In this lesson, we will learn how to form beginning and end patterns using the cap (^) and dollar($) metacharacters respectively.

3. Metacharacters Parentheses

In this lesson, we will look at it another important metacharacter, which is ().

1. String Modification

This video introduces you to the concept of string modification.

2. Word Tokenizer Using Split Method

In this lesson, we will learn how to build a simple word tokenizer using the split function.

3. Sub Method Exercise

Let's take a look at an example of string replacement or pattern replacement in this session.

4. Sub Method Exercise Solution

In this session, we will discuss the solution to the problem we discussed in the previous lesson.

1. What is a Word

Let's understand what a word is in the session.

2. Definition of Word is Task Dependent

Let's continue the discussion on âEUR~word' in this session and look at an example.

3. Vocabulary and Corpus

Let's understand the concept of vocabulary and corpus in text preprocessing.

4. Tokens

In this session, we will explore tokens.

5. Tokenization in Spacy

In this session, we will take a look at a power Python package called SpaCY.

1. Yelp Reviews Classification Mini Project Introduction

In this lesson, we will work with real data and perform data cleaning using Python.

2. Yelp Reviews Classification Mini Project Vocabulary Initialization

In this lesson, we will start data preparation for the Yelp Review Project.

3. Yelp Reviews Classification Mini Project Adding Tokens to Vocabulary

In this lesson, we will go ahead and add tokens to the vocabulary.

4. Yelp Reviews Classification Mini Project Look Up Functions in Vocabulary

In this lesson, we will add look up functions in the vocabulary.

5. Yelp Reviews Classification Mini Project Building Vocabulary from Data

In this lesson, we will add another function that will take a data frame as an input and build the vocabulary.

6. Yelp Reviews Classification Mini Project One-Hot Encoding

In this video, you will learn the process of one-hot encoding that enables us to change the data into vector form.

7. Yelp Reviews Classification Mini Project One-Hot Encoding Implementation

By now, you should be familiar with one-hot encoding. Let's implement this concept in this session.

8. Yelp Reviews Classification Mini Project Encoding Documents

In this lesson, you will learn the process of encoding documents.

9. Yelp Reviews Classification Mini Project Encoding Documents Implementation

Now that you are familiar with encoding documents, let's go ahead and implement it in this lesson.

10. Yelp Reviews Classification Mini Project Train Test Splits

In this video, you will learn to use train test splits.

11. Yelp Reviews Classification Mini Project Feature Computation

In this session, we will discuss feature computation.

12. Yelp Reviews Classification Mini Project Classification

In this session, we will discuss classification.

1. Tokenization in Detial Introduction

In this lesson, we will explore the concept of text normalization.

2. Tokenization is Hard

In this session, we will explore space beast tokenization.

3. Tokenization Byte Pair Encoding

Let's understand the data-driven approach using byte pair encoding in this session.

4. Tokenization Byte Pair Encoding Example

In this session, we will take a look at an example of byte pair encoding for better understanding.

5. Tokenization Byte Pair Encoding on Test Data

Let's apply byte pair encoding on test data in this session.

6. Tokenization Byte Pair Encoding Implementation Get Pair Counts

In this video, we will start implementation of byte pair encoding to get pair counts.

7. Tokenization Byte Pair Encoding Implementation Merge in Corpus

LetâEUR~s continue implementation of byte pair encoding in this session. We will merge the best pair in corpus.

8. Tokenization Byte Pair Encoding Implementation BFE Training

In this session, we will create the entire training setup that will generate the byte pair encoding statistics.

9. Tokenization Byte Pair Encoding Implementation BFE Encoding

In this session, we will take an example word and find out its tokenization.

10. Tokenization Byte Pair Encoding Implementation BFE Encoding One Pair

In this session, we will add a function that gets the pair merged based on the byte pair encoding statistics received during the training.

11. Tokenization Byte Pair Encoding Implementation BFE Encoding One Pair 1

In this lesson, we will write a function that will encode any new word using byte pair encoding.

1. Word Normalization Case Folding

In this session, letâEUR~s take a look at a few preprocessing issues that one might encounter and how we can use normalization techniques to overcome them.

2. Word Normalization Lemmatization

In this session, we will discuss the normalization techniqueâEUR"lemmatization.

3. Word Normalization Stemming

In this session, you will learn about stemming, which is a type of lemmatization.

4. Word Normalization Sentence Segmentation

In this session, let's look at an algorithm to understand the concept of sentence segmentation.

1. Spelling Correction Minimum Edit Distance Introduction

Learn how to use the minimum edit distance algorithm to achieve spelling correction.

2. Spelling Correction Minimum Edit Distance Example

Learn to differentiate between two words using minimum edit distance. Here is an example of minimum edit distance calculation.

3. Spelling Correction Minimum Edit Distance Table Filling

Learn to calculate minimum edit distance in this session.

4. Spelling Correction Minimum Edit Distance Dynamic Programming

Let's understand the concept of spelling correction using minimum edit distance in a little more detail before we start writing the code.

5. Spelling Correction Minimum Edit Distance Pseudocode

Before we start writing our code in Python, let's first write the pseudocode to calculate the minimum edit distance.

6. Spelling Correction Minimum Edit Distance Implementation

Learn to write the minimum edit distance algorithm in Python in this lesson.

7. Spelling Correction Minimum Edit Distance Implementation Bug fixing

We will continue writing our Python code for minimum edit distance and fix bugs in this lesson.

8. Spelling Correction Implementation

We will use the edit distance package in this session to build a spelling correction application.

1. What is a Language Model

This video introduces you to the concept of language modeling.

2. Language Model Formal Definition

This video session provides the language model definition.

3. Language Model Curse of Dimensionality

In this lesson, you will learn how dimensionality is an important factor in language modeling.

4. Language Model Markov Assumption and N-Grams

In this session, we will learn about Markov assumption: n-gram.

5. Language Model Implementation Setup

In this session, we will implement the concepts about language modeling that we have learned so far.

6. Language Model Implementation N-grams Function

We will start writing our code to build the language model in this session.

7. Language Model Implementation Update Counts Function

In this session, we will update the count function.

8. Language Model Implementation Probability Model Function

In this session, we will convert our model to probability values rather than counts.

9. Language Model Implementation Reading Corpus

In this session, we will be importing some real data.

10. Language Model Implementation Sampling Text

So far, we have successfully created our model. It's time to check whether it works. In this session, we will be sampling text.

1. One-Hot Vectors

In this video, we will learn about word representations in vector space.

2. One-Hot Vectors Implementation

Learn how to implement one-hot vector encoding.

3. One-Hot Vectors Limitations

This video provides a detailed explanation about the limitations of one-hot vectors.

4. One-Hot Vectors Used as Target Labeling

In this lesson, we will learn about target labeling.

5. Term Frequency for Document Representations

This video introduces you to the concept of document representation.

6. Term Frequency for Document Representations Implementations

In this session, we will write codes to get to the term frequency of a document.

7. Term Frequency for Word Representations

In this session, we will talk about term frequency for word representation.

8. TFIDF for Document Representations

In this lesson, you will learn about term frequency inverted document frequencyâEUR"TFIDF.

9. TFIDF for Document Representations Implementation Reading Corpus

In this session, we will implement the TFIDF model to represent different documents from scratch.

10. TFIDF for Document Representations Implementation Computing Document Frequency

In this session, we will compute the document frequency for each term.

11. TFIDF for Document Representations Implementation Computing TFIDF

In this video, we will compute the complete IDF vector.

12. Topic Modeling with TFIDF 1

In this session, we will implement topic modeling with TFIDF.

13. Topic Modeling with TFIDF 2

In this session, we're going to add a function that will build a model handy for the FIDF transformations.

14. Topic Modeling with TFIDF 3

In this session, we're going to write a function for TFIDF having the models of TFIDF transformer.

15. Topic Modeling with TFIDF 4

In this session, we will train our classifier.

16. Topic Modeling with Gensim

In this session, we will import corpora models and similarities from Gensim for our corpus.

1. Word Co-Occurrence Matrix

This video explains the concept of word co-occurrence matrix/term âEUR" term matrix/context - term matrix.

2. Word Co-Occurrence Matrix Versus Document-Term Matrix

In this session, we will look at the difference between word co-occurrence matrix and word document matrix.

3. Word Co-Occurrence Matrix Implementation Preparing Data

In this session, we will prepare our dataset for computing the word co-occurrence matrix.

4. Word Co-Occurrence Matrix Implementation Preparing Data 2

In this session, we will focus on more frequent words.

5. Word Co-Occurrence Matrix Implementation Preparing Data Getting Vocabulary

In this session, you will learn how to compute the vocabulary for the process list.

6. Word Co-Occurrence Matrix Implementation Final Function

In this session, let's add a function that computes the word co-occurrence matrix.

7. Word Co-Occurrence Matrix Implementation Handling Memory Issues on Large Corpora

In this lesson, you will learn how to handle memory issues on large corpora.

8. Word Co-Occurrence Matrix Sparsity

This video explains the concept of sparsity.

9. Word Co-Occurrence Matrix Positive Point Wise Mutual Information PPMI

This video explains pointwise mutual information PPMI with examples.

10. PCA for Dense Embeddings

In this lesson, you will learn about PCA for dense embedding.

11. Latent Semantic Analysis

This lesson gives a detailed explanation about latent semantic analysis.

12. Latent Semantic Analysis Implementation

In the session, we will implement latent semantic analysis using truncated SVD.

1. Cosine Similarity

This video explains the concept of cosine similarity.

2. Cosine Similarity Getting Norms of Vectors

In this session, we will learn how to get norms of vectors with cosine similarity.

3. Cosine Similarity Normalizing Vectors

In this session, we will write a function for normalizing a vector.

4. Cosine Similarity with More than One Vector

In this session, we will learn to write a function for normalizing more than one vector.

5. Cosine Similarity Getting Most Similar Words in the Vocabulary

In this session you will learn how to get the most similar words in the vocabulary.

6. Cosine Similarity Getting Most Similar Words in the Vocabulary Fixing bug

In this session, let's fix a few bugs.

7. Cosine Similarity Word2Vec Embeddings

In this video, we will see how we can compute the similarity of one word with another word using cosine similarity.

8. Word Analogies

Let's look at word analogies in this session.

9. Words Analogies Implementation 1

In this session, you will learn how to write a function to get the analogy.

10. Word Analogies Implementation 2

Let's continue the discussion about the functions that we have added to get the analogy and fix a few bugs.

11. Word Visualizations

This video explains word visualizations and important concepts related to it.

12. Word Visualizations Implementation

In this video, we will learn how to apply PCA or any other kind of dimensionality reduction technique.

13. Word Visualizations Implementation 2

In this session, we will implement word visualization.

1. Static and Dynamic Embeddings

This video introduces you to the Word2Vec embeddings.

2. Self Supervision

In this session, we will discuss about some basic concepts of Word2Vec embeddings.

3. Word2Vec Algorithm Abstract

This session provides a step-by-step explanation of the Word2Vec algorithm.

4. Word2Vec: Why Negative Sampling

In this session, we will learn about negative sampling and why it is required.

5. Word2Vec: What is Skip Gram

Learn about Skip gram in this session.

6. Word2Vec: How to Define Probability Law

In this session, we will learn about the probability law and how we can define it.

7. Word2Vec Sigmoid

This session provides a detailed description of the sigmoid function and how it can be used to model probabilities.

8. Word2Vec Formalizing Loss Function

In this session, we will learn how to formalize the loss function

9. Word2Vec Loss Function

Maximizing the similarity between the target and the context is equivalent to minimizing the similarity of negative words. Let's continue our discussion on lost function in this session.

10. Word2Vec Gradient Descent Step

This session explains the gradient descent step.

11. Word2Vec Implementation Preparing Data

Let's go ahead and implement Word2Vec. The first step is to prepare the data.

12. Word2Vec Implementation Gradient Step

In this session, we will continue implementing Word2Vec and perform the gradient descent step.

13. Word2Vec Implementation Driver Function

In this session, we will go ahead and add the driver function.

1. Why RNNs for NLP

In this section, let's get introduced to the concept of deep learning.

2. PyTorch Installation and Tensors Introduction

In this session, we will learn how to install PyTorch.

3. Automatic Differentiation PyTorch

In this session, we will understand automatic differentiation in detail.

1. Why DNNs in Machine Learning

In this lesson, we will learn about deep neural networks and their importance in machine learning.

2. Representational Power and Data Utilization Capacity of DNN

Let's understand why deep neural networks are preferred with the help of universal approximation theorem.

3. Perceptron

In this video, we will learn about perceptron/neuron.

4. Perceptron Implementation

In this session, we will implement a simple perceptron.

5. DNN Architecture

In this session, we will dive deeper into the deep neural network architecture.

6. DNN Forwardstep Implementation

In the session, you will learn how to build a neural network with two computational layers and one output unit. The layers will contain different number of neurons.

7. DNN Why Activation Function is Required

In this video, you will get a detailed explanation about the activation function and why it is required.

8. DNN Properties of Activation Function

In this lesson, let's look at the properties of the activation function.

9. DNN Activation Functions in PyTorch

In this lesson, we will define an activation function in PyTorch.

10. DNN What is Loss Function

In this session, let's learn about the loss function (gradient descent) in depth.

11. DNN Loss Function in PyTorch

In this session, we will look at an example of lost function in PyTorch.

1. DNN Gradient Descent

In this lesson, we will dive deeper into gradient descent.

2. DNN Gradient Descent Implementation

In this lesson, we will understand the concept of gradient descent with the help of an example.

3. DNN Gradient Descent Stochastic Batch Minibatch

In this session, we will look at the different ways to implement gradient descent such as stochastic, minibatch, and batch.

4. DNN Gradient Descent Summary

Let's summarize everything we have learned about gradient descent in this session.

5. DNN Implementation Gradient Step

In this session, we will add the sigmoid activation function two hour code.

6. DNN Implementation Stochastic Gradient Descent

In this session, we will add a training function for stochastic gradient descent.

7. DNN Implementation Batch Gradient Descent

In this session, you will learn how to implement batch gradient descent.

8. DNN Implementation Minibatch Gradient Descent

In this session, we will implement minibatch gradient descent.

9. DNN Implementation in PyTorch

In this lesson, we will perform DNN implementation in PyTorch.

1. DNN Weights Initializations

In this session, we will learn about weight initialization.

2. DNN Learning Rate

In this session, we will understand what is step size, also known as learning rate.

3. DNN Batch Normalization

This video provides information about batch normalization and it's important.

4. DNN Batch Normalization Implementation

In this video, we will implement batch normalization using the PyTorch framework.

5. DNN Optimizations

In this session, we will learn about the different optimization techniques.

6. DNN Dropout

Learn all about dropouts in this video lesson.

7. DNN Dropout in PyTorch

In this session, let's implement a dropout layer in our model.

8. DNN Early Stopping

In this lesson, you will learn about early stopping.

9. DNN Hyperparameters

Let's take a look at the list of all the hyperparameters we have learned so far.

10. DNN PyTorch CIFAR10 Example

In this session, we will implement a deep neural network in PyTorch using a real datasetâEUR"CIFAR 10.

1. What is RNN

Let's understand RNN with the help of an example in this session.

2. Understanding RNN with a Simple Example

In this lesson, let's understand vocabulary index for this project.

3. RNN Applications Human Activity Recognition

In this session, we will discuss about the various applications of RNN in human activity recognition.

4. RNN Applications Image Captioning

Let's understand the application of RNN in image captioning.

5. RNN Applications Machine Translation

In this video, we will learn about the application of RNN in machine translation.

6. RNN Applications Speech Recognition Stock Price Prediction

In this lesson, we will take a look at the application of RNN in speech recognition and stock price prediction.

7. RNN Models

In this video, we will cover the different RNN models in details.

1. Language Modeling Next Word Prediction

This video provides an overview of the language modeling mini-project.

2. Language Modeling Next Word Prediction Vocabulary Index

In this lesson, let's understand vocabulary index for this particular project.

3. Language Modeling Next Word Prediction Vocabulary Index Embeddings

In this session, you will learn the vocabulary index embedding that will be used in the mini project.

4. Language Modeling Next Word Prediction RNN Architecture

This section provides a detailed explanation of the RNN architecture for this particular project.

5. Language Modeling Next Word Prediction Python 1

Now that we have discussed the project in detail, it's time to start coding.

6. Language Modeling Next Word Prediction Python 2

Let's continue with our coding in this session as well. We will define the weight matrices and set the gradients to be true.

7. Language Modeling Next Word Prediction Python 3

Let's continue with our coding and define the forward step in this session.

8. Language Modeling Next Word Prediction Python 4

In this session, we will continue coding for the language model.

9. Language Modeling Next Word Prediction Python 5

In this session, we will implement the loss function in our model.

10. Language Modeling Next Word Prediction Python 6

In this lesson, we will define the train function.

1. Vocabulary Implementation

In this session, we will start working on our project with vocabulary implementation.

2. Vocabulary Implementation Helpers

In this session, we will add some tokens to our code.

3. Vocabulary Implementation From File

In this session, we will add a function that will build a vocabulary from the data frame.

4. Vectorizer

In this lesson, we will add a function to vectorize the reviews followed by building the RNN architecture.

5. RNN Setup

We will continue setting up RNN in this session.

6. RNN Setup 1

In this session, we will continue with our coding and add the sigmoid function.

1. RNN In PyTorch Introduction

This video provides a short recap followed by an overview of the entire section.

2. RNN in PyTorch Embedding Layer

In this session, we will first import a few modules followed by embedding layers.

3. RNN in PyTorch Nn Rnn

In this session, we will define a vocabulary size followed by the index vector.

4. RNN in PyTorch Output Shapes

In this session, we will apply the RNN to the inputs.

5. RNN in PyTorch Gated Units

In this session, let's learn about the different gated models.

6. RNN in PyTorch Gated Units GRU LSTM

In this session, you will learn how to replace a simple RNN with gated units GRU and LSTM.

7. RNN in PyTorch Bidirectional RNN

In this session, we will learn about bidirectional RNN.

8. RNN in PyTorch Bidirectional RNN Output Shapes

In this lesson, you will learn how to implement a bidirectional RNN.

9. RNN in PyTorch Bidirectional RNN Output Shapes Separation

In this session, we will learn how to separate the output shapes.

10. RNN in PyTorch Example

In this lesson, we will build simple RNN model using the PyTorch interface.

1. RNN Encoder Decoder

In this session, we will discuss about the encoder-decoder model.

2. RNN Attention

In this lesson, we will understand the attention mechanism.

1. Introduction to Dataset and Packages

In this lesson, we will look at the dataset and packages that we're going to use to build the encoder-decoder model.

2. Implementing Language Class

In this session, we will build a class for each language.

3. Testing Language Class and Implementing Normalization

In this lesson, we will test the class we created in our previous lesson.

4. Reading Datafile

In this session, we will define a function to read the data from the file.

5. Reading Building Vocabulary

In this lesson, we will be working on building the vocabulary.

6. EncoderRNN

Now that we have prepared all the data and the helper functions are in place, let's go ahead and define the encoder RNN class in this session.

7. DecoderRNN

In this session, we will add the codes for decoder RNN.

8. DecoderRNN Forward Step

In this session, we will be defining the forward function.

9. DecoderRNN Helper Functions

In this session, we will define some auxiliary functions.

10. Training Module

In this session, we will define the training routine.

11. Stochastic Gradient Descent

In this session, we will implement stochastic gradient decent.

12. NMT Training

In this session, we will cover an NMT training.

13. NMT Evaluation

In this session, we will cover an NMT evaluation.