Book Image

Transformers for Natural Language Processing

By : Denis Rothman
Book Image

Transformers for Natural Language Processing

By: Denis Rothman

Overview of this book

The transformer architecture has proved to be revolutionary in outperforming the classical RNN and CNN models in use today. With an apply-as-you-learn approach, Transformers for Natural Language Processing investigates in vast detail the deep learning for machine translations, speech-to-text, text-to-speech, language modeling, question answering, and many more NLP domains with transformers. The book takes you through NLP with Python and examines various eminent models and datasets within the transformer architecture created by pioneers such as Google, Facebook, Microsoft, OpenAI, and Hugging Face. The book trains you in three stages. The first stage introduces you to transformer architectures, starting with the original transformer, before moving on to RoBERTa, BERT, and DistilBERT models. You will discover training methods for smaller transformers that can outperform GPT-3 in some cases. In the second stage, you will apply transformers for Natural Language Understanding (NLU) and Natural Language Generation (NLG). Finally, the third stage will help you grasp advanced language understanding techniques such as optimizing social network datasets and fake news identification. By the end of this NLP book, you will understand transformers from a cognitive science perspective and be proficient in applying pretrained transformer models by tech giants to various datasets.
Table of Contents (16 chapters)
Other Books You May Enjoy

Context and completion examples

In this section, we will interact with a GPT-2 117M model trained on our dataset. We will first generate an unconditional sample that requires no input on our part. Then we will enter a context paragraph to obtain a conditional text completion response from our trained model.

Let's first run an unconditional sample:

#@title Step 11: Generating Unconditional Samples
import os # import after runtime is restarted
!python --model_name '117M'

You will not be prompted to enter context sentences since this is an unconditional sample generator.

To stop the cell, double-click on the run button of the cell or type Ctrl + M.

The result is random but makes sense from a grammatical perspective. From a semantic point of view, the result is not as interesting because we provided no context. But still, the process is remarkable. It invents posts, writes a...