Oreilly – Natural Language Processing (NLP) Fundamentals, 3rd Edition 2025-3

Natural Language Processing (NLP) Fundamentals, 3rd Edition. This course teaches the fundamentals and advanced aspects of natural language processing in a simple and practical way, and provides the tools necessary to use NLP in real-world projects. Using the NLTK library, it first covers basic concepts such as text representation, data cleaning, topic detection, regular expressions, and sentiment analysis. Then, using the PyTorch framework, it covers more advanced topics such as text classification and sequence-by-sequence models. It also analyzes the transformer architecture that underlies large language models such as ChatGPT and BERT, along with its practical applications. By the end of this course, students will have a comprehensive understanding of NLP tools and algorithms. Course topics include text representation, data cleaning, named entity recognition, topic modeling, sentiment analysis, text classification, sequence modeling, practical applications, and use of large language models. Each lesson is accompanied by practical examples to teach concepts in a tangible way.

What you will learn

• Implementing tokenization and text representation.
• Use of one-hot encodings and bag of words.
• Identifying related words using TF-IDF.
• Text cleaning through stemming and lemmatization techniques.
• Pattern matching using regular expressions.
• Understanding named entity recognition.
• Document clustering and topic modeling using various algorithms.
• Conduct sentiment analysis, including managing negations and modifiers.
• Using word embeddings to capture semantic relationships.
• Definition of GloVe.
• Modeling sequences in PyTorch with RNNs, GRUs, and LSTM networks.
• Transfer learning.
• Apply language recognition.
• Understanding and using transformers.
• Using LLMs for NLP tasks.
• Building NLP applications with HuggingFace and large language models.

This course is suitable for people who:

• Data scientists with an interest in natural language processing.

Course details

• Publisher: Oreilly
• Instructor: Bruno Goncalves
• Training level: Beginner to intermediate
• Training duration: 6 hours and 14 minutes

Course topics

• Introduction
• Lesson 1: Text Representation
• Topics
• 1.1 One-hot Encoding
• 1.2 Bag of Words
• 1.3 Stop Words
• 1.4 TF-IDF
• 1.5 N-grams
• 1.6 Word Embeddings
• 1.7 Demo
• Lesson 2: Text Cleaning
• Topics
• 2.1 Stemming
• 2.2 Lemmatization
• 2.3 Regular Expressions
• 2.4 Text Cleaning Demo
• Lesson 3: Named Entity Recognition
• Topics
• 3.1 Part of Speech Tagging
• 3.2 Chunking
• 3.3 Chinking
• 3.4 Named Entity Recognition
• 3.5 Demo
• Lesson 4: Topic Modeling
• Topics
• 4.1 Explicit Semantic Analysis
• 4.2 Document Clustering
• 4.3 Latent Semantic Analysis
• 4.4 LDA
• 4.5 Non-negative matrix factorization
• 4.6 Demo
• Lesson 5: Sentiment Analysis
• Topics
• 5.1 Quantify Words and Feelings
• 5.2 Negations and Modifiers
• 5.3 Corpus-based Approaches
• 5.4 Demo
• Lesson 6: Text Classification
• Topics
• 6.1 Feed Forward Networks
• 6.2 Convolutional Neural Networks
• 6.3 Applications
• 6.4 Demo
• Lesson 7: Sequence Modeling
• Topics
• 7.1 Recurrent Neural Networks
• 7.2 Gated Recurrent Unit
• 7.3 Long Short-term Memory
• 7.4 Auto-encoder Models
• 7.5 Demo
• Lesson 8: Applications
• Topics
• 8.1 Word2vec Embeddings
• 8.2 GloVe
• 8.3 Transfer Learning
• 8.4 Language Detection
• 8.5 Demo
• Lesson 9: NLP with Large Language Models
• Topics
• 9.1 Large Language Models
• 9.2 Transformers
• 9.3 BERT
• 9.4 HuggingFace
• 9.5 NLP Tasks
• 9.6 Demo
• Summary

Pictures from the Natural Language Processing (NLP) Fundamentals, 3rd Edition course

Sample course video

Download link

Download Part 1 – 1 GB

Download Part 2 – 127 MB

File(s) password: www.downloadly.ir

File size

1.1 GB