Oreilly – Deep Learning for Natural Language Processing, Video Edition 2022-10

Description

Deep Learning for Natural Language Processing course, Video Edition. Meet the most challenging natural language processing problems and learn how to solve them using advanced deep learning! In the Deep Learning for Natural Language Processing course, you’ll learn a wealth of NLP insights, including:

• An overview of NLP and deep learning
• One-gram text displays
• Word tokens
• Text similarity models
• Sequential NLP
• Semantic role tagging
• NLP based on deep memory
• Linguistic structure
• Hyperparameters for deep NLP

Deep learning has taken natural language processing to exciting new levels and powerful new applications! For the first time, computer systems can achieve “human” levels of summarizing, making connections, and other tasks that require understanding and context. Deep learning for natural language processing reveals the groundbreaking techniques that make these innovations possible.

What you will learn in this course

• Improving question answering with sequential NLP
• Performance enhancement with multitasking language learning
• Detailed interpretation of linguistic structure
• Mastery of different word tokenization techniques

This course is suitable for people who

• Readers with intermediate Python skills and general knowledge of NLP.
• No previous experience in deep learning is required.

Details of Deep Learning for Natural Language Processing course, Video Edition

• Publisher: Oreilly
• Lecturer: Stephan Raaijmakers
• Training level: beginner to advanced
• Training duration: 5 hours and 48 minutes

Course headings

• Part 1. Introduction
• Chapter 1. Deep learning for NLP
• Chapter 1. Deep learning
• Chapter 1. Vector representations of language
• Chapter 1. Vector sanitization
• Chapter 1. Summary
• Chapter 2. Deep learning and language: The basics
• Chapter 2. Deep learning and NLP: A new paradigm
• Chapter 2. Summary
• Chapter 3. Text embeddings
• Chapter 3. From words to vectors: Word2Vec
• Chapter 3. From documents to vectors: Doc2Vec
• Chapter 3. Summary
• Part 2. Deep NLP
• Chapter 4. Textual similarity
• Chapter 4. The data
• Chapter 4. Data representation
• Chapter 4. Models for measuring similarity
• Chapter 4. Summary
• Chapter 5. Sequential NLP
• Chapter 5. Data and data processing
• Chapter 5. Question Answering with sequential models
• Chapter 5. Summary
• Chapter 6. Episodic memory for NLP
• Chapter 6. Data and data processing
• Chapter 6. Strongly supervised memory networks: Experiments and results
• Chapter 6. Semi-supervised memory networks
• Chapter 6. Summary
• Part 3. Advanced topics
• Chapter 7. Attention
• Chapter 7. Data
• Chapter 7. Static attention: MLP
• Chapter 7. Temporal attention: LSTM
• Chapter 7. Experiments
• Chapter 7. Summary
• Chapter 8. Multitask learning
• Chapter 8. Multitask learning
• Chapter 8. Multitask learning for consumer reviews: Yelp and Amazon
• Chapter 8. Multitask learning for Reuters topic classification
• Chapter 8. Multitask learning for part-of-speech tagging and named-entity recognition
• Chapter 8. Summary
• Chapter 9. Transformers
• Chapter 9. Transformer encoders
• Chapter 9. Transformer decoders
• Chapter 9. BERT: Masked language modeling
• Chapter 9. Summary
• Chapter 10. Applications of Transformers: Hands-on with BERT
• Chapter 10. A BERT layer
• Chapter 10. Training BERT on your data
• Chapter 10. Fine-tuning BERT
• Chapter 10. Inspecting BERT
• Chapter 10. Applying BERT
• Chapter 10. Summary

Course images

Sample video of the course

download link

Download file – 769 MB

File(s) password: www.downloadly.ir

File size

769 MB