The Ultimate Beginners Guide to Natural Language Processing

Name: The Ultimate Beginners Guide to Natural Language Processing
Rating: 4.3 (734 reviews)

Learn step-by-step the main concepts of natural language processing in Python! Build a sentiment classifier!

Created byJones Granatyr, AI Expert Academy

Last updated 4/2023

English

What you'll learn

Understand the basic concepts of natural language processing, such as: part-of-speech, lemmatization, stemming, named entity recognition, and stop words
Understand more advanced concepts, such as: dependency parsing, tokenization, word and sentence similarity
Load texts from the Internet to apply natural language processing techniques
How to visualize the most frequent terms using wordcloud
Implement text summarization and keyword search
Learn how to represent texts using Bag of Words and TF-IDF
Implement sentiment analysis using NLTK library (natural language toolkit), TF-IDF and spaCy library

Course content

5 sections • 49 lectures • 6h 5m total length

Course content9:22
Introduction to natural language processing4:51
Course materials0:13

Plan of attack2:48
Learn natural language processing basics with spaCy, covering parts of speech, lemmatization vs stemming, named entity recognition, stopwords, dependency parsing, and word similarity.
Installing the libraries6:47
Install the spaCy library in Google Colab, explore its language support, and enable NLP tasks such as named entity recognition, sentence segmentation, part of speech, dependency parsing, and text classification.
POS (part-of-speech)12:59
Lemmatization and stemming10:36
Named entity recognition7:50
Learn how named entity recognition identifies and classifies entities such as people, locations, dates, and money in text, with examples like IBM, U.S., San Francisco, 2018, and $320 billion.
Stop words7:58
Dependency parsing 16:51
Dependency parsing 28:14
Dependency parsing 35:21
Dependency parsing 45:04
Implement a dependence parsing example and recap concepts using cities and actions identified by named entity recognition. Print locations and actions and illustrate how visit relates to stay through relations.
Word similarity 16:21
Word similarity 24:10
Word tokenization5:04

Plan of attack3:29
Loading texts from the Internet6:17
Named entity recognition4:23
Most frequent words5:43
Word cloud3:57
Generate word clouds from cleaned text to visualize common words. Note how word clouds remove stopwords and punctuation, while Nltk may not, with preprocessing and frequency comparison.
Preprocessing the texts11:44
Text summarization - intuition11:58
Explore the intuition of a frequency-based text summarization algorithm, covering pre-processing, word frequency and weights, sentence tokenization, and scoring to select top sentences for the summary.
Text summarization - implementation14:45
Keyword search17:02
Bag of words - intuition4:12
Bag of words - implementation7:01
TF-IDF - intuition14:20
TF-IDF - implementation8:05
Cosine similarity11:47
Simulating a chatbot 14:25
Simulate a chatbot using cosine similarity to match user greetings to predefined responses, tokenize input with split, normalize case, and return a random welcome message.
Simulating a chatbot 212:15
Develop a chatbot by implementing an answer function that preprocesses user input, applies tf-idf with cosine similarity, and returns the most relevant natural language processing sentence or a no-answer message.
Simulating a chatbot 34:28

Plan of attack3:49
Loading the Twitter dataset10:10
Load and explore the Twitter dataset in Google Colab, install Spacey, and prepare the text and sentiment columns for a sentiment analysis study.
Train and test data9:41
Preprocessing the texts8:44
Word cloud3:17
Detecting languages5:31
Sentiment analysis with NLTK6:15
Introduction to classification and decision trees8:37
Explore classification and decision trees through a bank loan dataset, using training dataset to build a tree that predicts risk based on income and credit history.
Sentiment analysis - TF-IDF 19:57
Sentiment analysis - TF-IDF 210:42
Sentiment analysis - spaCy 110:42
Train a custom sentiment analyzer with spaCy, building a two-class (positive and negative) classifier from a simple dataset and a text classification pipe.
Sentiment analysis - spaCy 210:53
This lecture trains a spaCy sentiment classifier with a neural network. It covers epochs, data shuffling, mini-batches, doc creation, annotations, and saving the model to disk.
Sentiment analysis - spaCy 36:03
Sentiment analysis - spaCy 47:25
Evaluate the spaCy sentiment classifier on the test data, compare accuracy with tf-idf, and review the classification report and confusion matrix. Learn to build a custom sentiment analyzer using spaCy.

Requirements

Programming logic
Basic Python programming

Description

The area of Natural Language Processing (NLP) is a subarea of Artificial Intelligence that aims to make computers capable of understanding human language, both written and spoken. Some examples of practical applications are: translators between languages, translation from text to speech or speech to text, chatbots, automatic question and answer systems (Q&A), automatic generation of descriptions for images, generation of subtitles in videos, classification of sentiments in sentences, among many others! Learning this area can be the key to bringing real solutions to present and future needs!

Based on that, this course was designed for those who want to grow or start a new career in Natural Language Processing, using the spaCy and NLTK (Natural Language Toolkit) libraries and the Python programming language! SpaCy was developed with the focus on use in production and real environments, so it is possible to create applications that process a lot of data. It can be used to extract information, understand natural language and even preprocess texts for later use in deep learning models.

The course is divided into three parts:

In the first one, you will learn the most basic natural language processing concepts, such as: part-of-speech, lemmatization, stemming, named entity recognition, stop words, dependency parsing, word and sentence similarity and tokenization
In the second part, you will learn more advanced topics, such as: preprocessing function, word cloud, text summarization, keyword search, bag of words, TF-IDF (Term Frequency - Inverse Document Frequency), and cosine similarity. We will also simulate a chatbot that can answer questions about any subject you want!
Finally, in the third and last part of the course, we will create a sentiment classifier using a real Twitter dataset! We will implement the classifier using NLTK, TF-IDF and also the spaCy library

This can be considered the first course in natural language processing, and after completing it, you can move on to more advanced materials. If you have never heard about natural language processing, this course is for you! At the end you will have the practical background to develop some simple projects and take more advanced courses. During the lectures, the code will be implemented step by step using Google Colab, which will ensure that you will have no problems with installations or configurations of software on your local machine.

Who this course is for:

People interested in natural language processing
People interested in the spaCy and NLTK libraries
Students who are studying subjects related to Artificial Intelligence
Data Scientists who want to increase their knowledge in natural language processing

The Ultimate Beginners Guide to Natural Language Processing

What you'll learn

Explore related topics

Course content

Introduction3 lectures • 14min

Basic NLP - spaCy library13 lectures • 1hr 30min

Summarization, search, representation, and similarity17 lectures • 2hr 26min

Sentiment analysis14 lectures • 1hr 52min

Final remarks2 lectures • 3min

Requirements

Description

Who this course is for: