Natural Language Processing Fundamentals

This lesson emphasizes on basic feature extraction methods in detail and also visualize text with the help of word clouds and other visualization techniques.

To deal with data effectively, we need to understand the various forms in which it exists. Let's first understand the types of data that exist. There are two main ways to categorize data, by structure and by content, as explained in this video.

Data cleaning is the art of extracting meaningful portions from data by eliminating unnecessary details. To perform data cleaning, let us use the most common methods such as tokenization and stemming. In this video, we’ll cover:

• Tokenization

• Types of Tokenizers

Through this video, we’ll see how data cleaning is done thought stemming. In this video, we’ll cover:

• Stemming

• Lemmatization

• Language Translation

• Stop Word Removal

When dealing with texts, we extract both general and specific features. Sometimes, individual words constituting texts do not affect some features directly, such as the language of the text and the total number of words. These features can be referred to as general features. Specific features include bag of words, and TF-IDF representations of texts. Let's understand these in this video.

Feature engineering is a method for extracting new features from existing features. These new features are extracted as they tend to effectively explain variability in data. One application of feature engineering could be to calculate how similar different pieces of text are. There are various ways of calculating the similarity between two texts. The most popular methods are cosine similarity and Jaccard similarity. Let's learn about each of them:

Let us now summarize our learning from this lesson.

In this lesson, you will learn about the various types of machine learning algorithms and develop classifiers with their help.

Machine learning refers to the process of comprehending the patterns present in a dataset. In this video, we’ll cover:

• Unsupervised Learning

• Supervised Learning

• Classification

In this video, we’ll continue exploring machine learning. We’ll cover the following:

• Regression

• Random Forest

• GBM and XG-Boost

• Sampling

A text classifier is a machine learning model that can discriminate between texts based on their content. In this video, we’ll be developing a text classifier.

A pipeline refers to a structure that allows a streamlined flow of air, water, or something similar. In this context, pipeline has a similar meaning. It helps to streamline various stages of an NLP project. In this video, you will learn how to build pipelines for NLP projects.

In this video, we’ll have a look at how to save and load models.

Let us now summarize our learning from this lesson.

In this lesson, you will learn how to collect data from different file formats.

In this video, you will learn about collecting data by scraping web pages and then processing it.

We have just learned how to extract tag-based information from an HTML file. Now, through this video, let us focus on fetching content from web pages.

Now that we have learned how to fetch data from online sources and analyze it in various ways. In this video, let us discuss dealing with semi-structured data.

Let us now summarize our learning from this lesson.

In this lesson, you will learn about different topic modeling algorithms and how we can use them to perform topic modeling on any dataset.

In this video, we will cover the following subtopics:

• Discovering Themes

• Exploratory Data Analysis

• Document Clustering

• Dimensionality Reduction

• Historical Analysis

• Bag of Words

In this video, we will cover two topic modeling algorithms, namely LSA and LDA.

We have performed topic modeling with the help of LDA. Now, let us focus on topic fingerprinting.

Let us now summarize our learning from this lesson.

In this lesson, you will learn about the various ways in which text can be summarized and generated.

Automated text summarization is the process of using natural language processing (NLP) tools to produce concise versions of text that preserve all the key information present in the original content. In this video, we will look at some of the benefits provided by automated text summarization.

We will discuss each aspect of text summarization in detail in this video.

TextRank is a popular algorithm for extractive text summarization. It works on the principle of ranking pages based on the total number of other pages referring to a given page. Let us look at how this algorithm works along with a demonstration.

Now, let us understand how to summarize text using different methods such as using the Gensim library and using word frequency. This video also covers how to generate text using Markov chains.

Let us now summarize our learning from this lesson.

In this lesson, you will be learning about various encoding techniques using which a text can be represented as vector.

In this video, we will look at how text can be represented as vectors, and how vectors can be composed to represent complex speech.

The process of converting data into a specified format is called encoding. Let us now look at the different types of encoding that are required to convert text into vectors.

In this video, we will focus on concepts such as embeddings and word embeddings. We will learn about the Word2Vec algorithm, which is used to train word vectors. We’ll also look at document vectors and their uses.

Let us now summarize our learning from this lesson.

This lesson explains the concepts of sentiment analysis and how to use it to detect various sentiments in the data.

Let us now see what sentiment analysis is. This video is all about sentiment analysis and covers the growth, types, and applications of sentiment analysis.

There are a lot of tools capable of analyzing sentiment. Each tool has its advantages and disadvantages. We will look at each of them in detail through this video.

TextBlob is a Python library used for NLP with a simple API. It is probably the easiest way to begin with sentiment analysis and other text analytic areas in Python. In this video, we will perform a demonstration to get a better understanding of how TextBlob is used in sentiment analysis.

Sentiment analysis is a type of text classification. Sentiment analysis models are usually trained using supervised datasets. In this video, we will look at how to load data for sentiment analysis through a short demonstration.

The end product of any sentiment analysis project is a sentiment model. In this video, we will solve an exercise to get a better understanding of training a sentiment model.

Let us now summarize our learning from this lesson.