Oreilly – Real-World Natural Language Processing, Video Edition 2021-11

Published on: 2024-12-12 17:49:34

Categories: 28

Description

Real-World Natural Language Processing Video Edition. In this video course, a narrator reads the book while the content, diagrams, code listings, and text are displayed on the screen. This course is like an audiobook that you can also watch as a video. Real-World Natural Language Processing teaches you how to build practical applications of natural language processing without getting bogged down in the complex theory of language and the mathematics of deep learning. In this engaging book, you’ll explore the core tools and techniques needed to build a wide range of powerful natural language processing applications, including chatbots, language recognizers, and text classifiers.

Training computers to interpret and produce speech and text is a major challenge, and the rewards are reduced labor and improved human-computer interaction! The field of natural language processing (NLP) is rapidly advancing, with countless new tools and methods accompanying it. This unique book presents an innovative collection of natural language processing techniques with applications in machine translation, voice assistants, text generation, and more.

What you will learn:

Design, develop, and deploy useful natural language processing applications
Creating entity name taggers
Building machine translation systems
Building language generation systems and chatbots
Using advanced natural language processing concepts such as attention and transfer learning

This course is suitable for people who:

They are Python programmers.
They do not require prior knowledge of machine learning.

Real-World Natural Language Processing Video Edition Course Specifications

Publisher: Oreilly
Instructor: Masato Hagiwara
Training level: Beginner to advanced
Training duration: 9 hours and 47 minutes

Course headings

Part 1. Basics
Chapter 1. Introduction to natural language processing
Chapter 1. How NLP is used
Chapter 1. Building NLP applications
Chapter 1. Summary
Chapter 2. Your first NLP application
Chapter 2. Working with NLP datasets
Chapter 2. Using word embeddings
Chapter 2. Neural networks
Chapter 2. Loss functions and optimization
Chapter 2. Training your own classifier
Chapter 2. Evaluating your classifier
Chapter 2. Deploying your application
Chapter 2. Summary
Chapter 3. Word and document embeddings
Chapter 3. Building blocks of language: Characters, words, and phrases
Chapter 3. Tokenization, stemming, and lemmatization
Chapter 3. Skip-gram and continuous bag of words (CBOW)
Chapter 3. GloVe
Chapter 3. fastText
Chapter 3. Document-level embeddings
Chapter 3. Visualizing embeddings
Chapter 3. Summary
Chapter 4. Sentence classification
Chapter 4. Long short-term memory units (LSTMs) and gated recurrent units (GRUs)
Chapter 4. Accuracy, precision, recall, and F-measure
Chapter 4. Building AllenNLP training pipelines
Chapter 4. Configuring AllenNLP training pipelines
Chapter 4. Case study: Language detection
Chapter 4. Summary
Chapter 5. Sequential labeling and language modeling
Chapter 5. Building a part-of-speech tagger
Chapter 5. Multilayer and bidirectional RNNs
Chapter 5. Named entity recognition
Chapter 5. Modeling a language
Chapter 5. Text generation using RNNs
Chapter 5. Summary
Part 2. Advanced models
Chapter 6. Sequence-to-sequence models
Chapter 6. Machine translation 101
Chapter 6. Building your first translator
Chapter 6. How Seq2Seq models work
Chapter 6. Evaluating translation systems
Chapter 6. Case study: Building a chatbot
Chapter 6. Summary
Chapter 7. Convolutional neural networks
Chapter 7. Convolutional layers
Chapter 7. Pooling layers
Chapter 7. Case study: Text classification
Chapter 7. Summary
Chapter 8. Attention and Transformer
Chapter 8. Sequence-to-sequence with attention
Chapter 8. Transformer and self-attention
Chapter 8. Transformer-based language models
Chapter 8. Case study: Spell-checker
Chapter 8. Summary
Chapter 9. Transfer learning with pretrained language models
Chapter 9. BERT
Chapter 9. Case study 1: Sentiment analysis with BERT
Chapter 9. Other pretrained language models
Chapter 9. Case study 2: Natural language inference with BERT
Chapter 9. Summary
Part 3. Putting into production
Chapter 10. Best practices in developing NLP applications
Chapter 10. Tokenization for neural models
Chapter 10. Avoiding overfitting
Chapter 10. Dealing with unbalanced datasets
Chapter 10. Hyperparameter tuning
Chapter 10. Summary
Chapter 11. Deploying and serving NLP applications
Chapter 11. Deploying your NLP model
Chapter 11. Case study: Serving and deploying NLP applications
Chapter 11. Interpreting and visualizing model predictions
Chapter 11. Where to go from here
Chapter 11. Summary