0% completed

All LessonsFree Lessons (7)

Getting Started

Introduction to the Course Overview: Getting Started NLP and Python Python String Operations High-level Overview of the spaCy Library Visualization with displaCy Summary: Getting Started Quiz: Getting Started Exercise: Getting Started Solution: Getting Started

Core Operations with spaCy

Overview: Core Operations with spaCy Overview of spaCy Conventions Introducing Tokenization Customizing the Tokenizer and Sentence Segmentation Understanding Lemmatization spaCy Container Objects More spaCy Features Summary: Core Operations with spaCy Quiz: Core Operations with spaCy Exercise: Core Operations with spaCy Solution: Core Operations with spaCy

Linguistic Features

Overview: Linguistic Features POS Tagging POS Tagging - Continued Introduction to Dependency Parsing Introducing NER Merging and Splitting Tokens Summary: Linguistic Features Quiz: Linguistic Features Exercise: Linguistic Features Solution: Linguistic Features

Rule-Based Matchmaking

Overview: Rule-Based Matchmaking Token Based Matching Syntax Support and Regex PhraseMatcher and EntityRuler Combining spaCy Models and Matchers Summary: Rule-Based Matchmaking Quiz: Rule-Based Matchmaking Exercise: Rule-Based Matchmaking Solution: Rule-Based Matchmaking

Working with Word Vectors and Semantic Similarity

Overview: Word Vectors and Semantic Similarity Understanding Word Vectors Using spaCy's Pre-trained Vectors The Similarity Method Advanced Semantic Similarity Methods Summary: Word Vectors and Semantic Similarity Quiz: Working with Word Vectors and Semantic Similarity Exercise: Word Vectors and Semantic Similarity Solution: Word Vectors and Semantic Similarity

Putting Everything Together: Semantic Parsing with spaCy

Overview: Semantic Parsing with spaCy Extracting Named Entities Using Dependency Trees For Extracting Entities Using Dependency Relations for Intent Recognition Semantic Similarity Methods for Semantic Parsing Putting It All Together Summary: Semantic Parsing with spaCy Quiz: Semantic Parsing with spaCy Exercise: Semantic Parsing with spaCy Solution: Semantic Parsing with spaCy

Course Assessment

Assessment: spaCy Features

Project

Auto-Tagging System for Content Categorization

Customizing spaCy Models

Overview: Customizing spaCy Models Getting Started with Data Preparation Updating an Existing Pipeline Component Training a Pipeline Component From Scratch Summary Quiz: Customizing spaCy Models Exercise: Customizing spaCy Models Solution: Customizing spaCy Models

Text Classification with spaCy

Overview: Text Classification with spaCy Understanding the Basics of Text Classification Training the spaCy Text Classifier Sentiment Analysis with spaCy Text classification with spaCy and Keras Embedding Words Summary: Text Classification with SpaCy Quiz: Text Classification with spaCy Exercise: Text Classification with spaCy Solution: Text Classification with spaCy

spaCy and Transformers

Overview: spaCy and Transformers

Transformers and Transfer Learning

Understanding BERT

Transformers and TensorFlow

Using BERT for Text Classification

Using Transformer Pipelines

Transformers and spaCy

Summary: spaCy and Transformers

Quiz: spaCy and Transformers

Exercise: spaCy and Transformers

Solution: spaCy and Transformers

Putting Everything Together: Designing a Chatbot with spaCy

Overview: Designing a Chatbot with spaCy Introduction to Conversational AI Getting to Know the Dataset Entity Extraction Intent Recognition Classifying Text with a Character-level LSTM Differentiating Subjects from Objects Anaphora Resolution Summary: Designing a Chatbot with spaCy Quiz: Designing a Chatbot With spaCy

Appendix

Installing spaCy Installing spaCy's Statistical Models More on Visualization with displaCy Saving and loading custom models

Conclusion

Course Assessment

Assessment - Machine Learning with spaCy

Mastering spaCy/

...

/

Using BERT for Text Classification

Using BERT for Text Classification

Let's use BERT to train a text classifier.

We'll cover the following...

In this lesson, we'll train a binary text classifier with BERT and tf.keras. We'll reuse some of the code we have used previously, but this time the code will be much shorter because we'll replace the embedding and LSTM layers with BERT. The complete code is available at the Jupyter notebook at the end. We'll skip the data preparation. We used the SMS Spam Collection dataset from Kaggle.

Let's get started by importing the BERT models and tokenizer:

Press + to interact

from transformers import BertTokenizer, TFBertModel, BertConfig, TFBertForSequenceClassification
bert_tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
bmodel = TFBertModel.from_pretrained("bert-base-uncased")

We have imported the BertTokenizer tokenizer and the BERT model, TFBertModel. We initialized both the tokenizer and the BERT model with the pre-trained bert-base-uncased model. Notice that the model's name ...