- Knowledge distillation is a model compression technique in which a small model is trained to reproduce the behavior of a large pre-trained model. It is also referred to as teacher-student learning, where the large pre-trained model is the teacher and the small model is the student.
- The output of the teacher network is called a soft target, and the prediction made by the student network is called a soft prediction.
- In knowledge distillation, we compute the cross-entropy loss between the soft target and soft prediction and train the student network through backpropagation by minimizing the cross-entropy loss. The cross-entropy loss between the soft-target and soft-prediction is also known as the distillation loss.
- The pre-trained BERT model has a large number of parameters and also high inference time, which makes it harder to use them on edge devices such as mobile phones. To solve this issue, we use DistilBERT, which...
Getting Started with Google BERT
By :
Getting Started with Google BERT
By:
Overview of this book
BERT (bidirectional encoder representations from transformer) has revolutionized the world of natural language processing (NLP) with promising results. This book is an introductory guide that will help you get to grips with Google's BERT architecture. With a detailed explanation of the transformer architecture, this book will help you understand how the transformer’s encoder and decoder work.
You’ll explore the BERT architecture by learning how the BERT model is pre-trained and how to use pre-trained BERT for downstream tasks by fine-tuning it for NLP tasks such as sentiment analysis and text summarization with the Hugging Face transformers library. As you advance, you’ll learn about different variants of BERT such as ALBERT, RoBERTa, and ELECTRA, and look at SpanBERT, which is used for NLP tasks like question answering. You'll also cover simpler and faster BERT variants based on knowledge distillation such as DistilBERT and TinyBERT. The book takes you through MBERT, XLM, and XLM-R in detail and then introduces you to sentence-BERT, which is used for obtaining sentence representation. Finally, you'll discover domain-specific BERT models such as BioBERT and ClinicalBERT, and discover an interesting variant called VideoBERT.
By the end of this BERT book, you’ll be well-versed with using BERT and its variants for performing practical NLP tasks.
Related Content you might be interested in
Current Title:
Getting Started with Google BERT
Table of Contents (15 chapters)
Preface
Section 1 - Starting Off with BERT
Free Chapter
A Primer on Transformers
Understanding the BERT Model
Getting Hands-On with BERT
Section 2 - Exploring BERT Variants
BERT Variants I - ALBERT, RoBERTa, ELECTRA, and SpanBERT
BERT Variants II - Based on Knowledge Distillation
Section 3 - Applications of BERT
Exploring BERTSUM for Text Summarization
Applying BERT to Other Languages
Exploring Sentence and Domain-Specific BERT
Working with VideoBERT, BART, and More
Assessments
Other Books You May Enjoy
Customer Reviews