Back To Course Home

Natural Language Processing with TensorFlow

0% completed

Introduction to Natural Language Processing

Introduction: Natural Language Processing What Is Natural Language Processing?Tasks of Natural Language Processing The Traditional Approach to Natural Language Processing The Deep Learning Approach to Natural Language Processing Summary: Introduction to Natural Language Processing

Understanding TensorFlow 2

Introduction: Understanding TensorFlow 2 What Is TensorFlow 2?TensorFlow 2 Architecture: Building and Executing Graphs Café Le TensorFlow 2: Understanding TensorFlow 2 with an Analogy Flashback: TensorFlow 1 Defining Inputs in TensorFlow Building a Data Pipeline Using the tf.data API Defining Variables and Output in TensorFlow Defining Operations in TensorFlow Neural Network-Related Operations Keras: TensorFlow's Model-Building API Implementing Our First Neural Network Summary: Understanding TensorFlow 2 Quiz: Understanding TensorFlow 2

Word2vec: Learning Word Embeddings

Introduction of Word2vec: Learning Word Embeddings Classical Approaches to Learning Word Representations An Intuitive Understanding of Word2vec The Skip-Gram Algorithm Data Generators in the Skip-Gram Algorithm with TensorFlow Implementing the Skip-Gram Architecture with TensorFlow Training and Evaluating the Skip-Gram Model The Continuous Bag-of-Words Algorithm Summary of Word2vec: Learning Word Embeddings Quiz of Word2vec: Learning Word Embeddings

Advanced Word Vector Algorithms

Introduction: Advanced Word Vector Algorithms

GloVe: Global Vectors Representation

Implementing GloVe

Generating Data for GloVe

Training and Evaluating GloVe

ELMo: Taking Ambiguities Out of Word Vectors

Preparing Inputs for ELMo

Generating Embeddings with ELMo

Dataset in Document Classification with ELMo

Generating Document Embeddings

Classifying Documents with Document Embeddings

Summary: Advanced Word Vector Algorithms

Quiz: Advanced Word Vector Algorithms

Sentence Classification with Convolutional Neural Networks

Introduction: Sentence Classification with CNNs Introducing CNNs Understanding CNNs: Convolution Operations Understanding CNNs: Pooling Operations Understanding CNNs: Fully Connected Layers Exercise: Image Classification on Fashion-MNIST with CNN CNNs for Sentence Classification: Transformation of Data CNNs for Sentence Classification: Downloading and Preparing Data CNNs for Sentence Classification: Building a Tokenizer The Sentence Classification CNN Model Sentence Classification with CNNs Summary: Sentence Classification with CNNs Quiz: Sentence Classification with CNNs

Recurrent Neural Networks

Introduction: Recurrent Neural Networks Understanding RNNs Backpropagation through Time Applications of RNNs Named Entity Recognition with RNNs: Preparing Data Named Entity Recognition with RNNs: Defining the Model Named Entity Recognition with RNNs: Training and Evaluation NER with Character and Token Embeddings Summary: Recurrent Neural Networks Quiz: Recurrent Neural Networks

Understanding Long Short-Term Memory Networks

Introduction: Understanding Long Short-Term Memory Networks Understanding Long Short-Term Memory Networks How LSTMs Solve the Vanishing Gradient Problem Improving LSTMs Other Variants of LSTMs Summary: Understanding Long Short-Term Memory Networks Quiz: Understanding Long Short-Term Memory Networks

Applications of LSTM: Generating Text

Introduction: Applications of LSTMs—Generating Text Understanding the Data Implementing the Language Model Generating New Text with the Model Comparing LSTMs to LSTMs with Peephole Connections and GRUs Improving Sequential Models: Beam Search Improving LSTMs: Generating Text with Words Instead of N-grams Summary: Applications of LSTMs—Generating Text Quiz: Applications of LSTMs—Generating Text

Sequence-to-Sequence Learning: Neural Machine Translation

Introduction: Sequence-to-Sequence Learning—NMT Machine Translation Understanding Neural Machine Translation Preparing Data for the NMT System Defining the NMT Model Attention: Analyzing, Computing, and Implementing Training the NMT The BLEU Score: Evaluating Machine Translation Systems Visualizing Attention Patterns Inference with NMT Other Applications of Seq2Seq Models: Chatbots Summary: Sequence-to-Sequence Learning—NMT Quiz: Sequence-to-Sequence Learning—NMT

Transformers

Introduction: Transformers Transformer Architecture: Encoder, Decoder, and Computing Output Transformer Architecture: Embedding Layers Transformer Architecture: Residuals and Normalization Understanding BERT Use Case: Using BERT to Answer Questions Use Case: Implementing BERT Training and Evaluating Model and Answering Questions with BERT Summary: Transformers Quiz: Transformers

Image Captioning with Transformers

Introduction: Image Captioning with Transformers Getting to Know the Data Processing and Tokenizing Data Defining a tf.data.Dataset The Machine Learning Pipeline for Image Caption Generation Implementing and Training the Model with TensorFlow Evaluating the Results Quantitatively Evaluating the Model and Generating Captions from It Summary: Image Captioning with Transformers Quiz: Image Captioning with Transformers

Final Remarks

Appendix: Mathematical Foundations and Advanced TensorFlow

Introduction to the Technical Tools Basic Data Structures Special Types of Matrices Probability Visualizing Word Embeddings with TensorBoard Summary: Appendix

GloVe: Global Vectors Representation

Learn about the GloVe algorithm for word embeddings.

We'll cover the following

Co-occurrence matrix
Understanding GloVe

One of the main limitations of the skip-gram and CBOW algorithms is that they can only capture local contextual information because they only look at a fixed-length window around a word. There’s an important part of the puzzle missing here because these algorithms don’t look at global statistics (by global statistics, we mean a way for us to see all the occurrences of words in the context of another word in a text corpus).

Get hands-on with 1200+ tech skills courses.