Natural Language Processing with Transformers, Revised Edition: Building Language Applications With Hugging Face - Softcover

Tunstall, Lewis; Von Werra, Leandro; Wolf, Thomas

Softcover

ISBN 10: 1098136799 ISBN 13: 9781098136796

Publisher: O'Reilly Media, 2022

Synopsis

Since their introduction in 2017, transformers have quickly become the dominant architecture for achieving state-of-the-art results on a variety of natural language processing tasks. If you're a data scientist or coder, this practical book -now revised in full color- shows you how to train and scale these large models using Hugging Face Transformers, a Python-based deep learning library.

About this title

About the Author

Lewis Tunstall is a data scientist at Swisscom, focused on building machine learning powered applications in the domains of natural language processing and time series. A former theoretical physicist, he has over 10 years experience translating complex subject matter to lay audiences and has taught machine learning to university students at both the graduate and undergraduate levels. Leandro von Werra is a data scientist at Swiss Mobiliar where he leads the company's natural language processing efforts to streamline and simplify processes for customers and employees. He has experience working across the whole machine learning stack, and is the creator of a popular Python library that combines Transformers with reinforcement learning. He also teaches data science and visualisation at the Bern University of Applied Sciences. Thomas Wolf is Chief Science Officer and co-founder of HuggingFace. His team is on a mission to catalyze and democratize NLP research. Prior to HuggingFace, Thomas gained a Ph.D. in physics, and later a law degree. He worked as a physics researcher and a European Patent Attorney.

Edition details

• Publisher: O'Reilly Media
• Publication date: 2022
• Language: English
• ISBN 10: 1098136799
• ISBN 13: 9781098136796
• Binding: Paperback
• Number of pages: 406