Natural Language Processing mit PyTorch

by Brian McMahan Frank Langenau Delip Rao

Natural Language Processing (NLP) offers unbounded opportunities for solving interesting problems in artificial intelligence, making it the latest frontier for developing intelligent, deep learning-based applications. If you're a developer or researcher ready to dive deeper into this rapidly growing area of artificial intelligence, this practical book shows you how to use the PyTorch deep learning framework to implement recently discovered NLP techniques. To get started, all you need is a machine learning background and experience programming with Python.Author Delip Rao provides you with a solid grounding in PyTorch, and deep learning algorithms, for building applications involving semantic representation of text. Each chapter includes several code examples and illustrations.Get extensive introductions to NLP, deep learning, and PyTorchUnderstand traditional NLP methods, including NLTK, SpaCy, and gensimExplore high quality representations for words in a languageLearn representations from a language sequence, using the Recurrent Neural Network (RNN)Improve on RNN results with complex neural architectures, such as Long Short Term Memories (LSTM) and Gated Recurrent UnitsExplore sequence-to-sequence models (used in translation) that read one sequence and produce another

Genres: Computer Science, Artificial Intelligence, Programming, Technology, Coding, Reference, Linguistics

Paperback

Published January 1, 2019

Reviews

[Vicki · Rating 4 out of 5]

Really dense and good overview of NLP. People completely new to the field might be lost but if you’ve already done at least some it puts all true concepts into good context with code.

[Jakob · Rating 4 out of 5]

Delip Rao’s “Natural Language Processing mit PyTorch” ist ein beeindruckendes Werk, das sich auf die Vermittlung von essenziellen NLP-Techniken und -Konzepten konzentriert. Es ist ein Buch, das sowohl für Anfänger als auch für Fortgeschrittene geeignet ist.

Das Buch ist gut organisiert und die Inhalte sind leicht verständlich. Rao hat einen ausgezeichneten Job gemacht, indem er die oft komplexen Themen des NLP auf eine zugängliche und praktische Weise präsentiert. Er bietet viele nützliche Beispiele und Anleitungen, die den Lesern helfen, die Konzepte in der Praxis anzuwenden.

Ein weiterer bemerkenswerter Aspekt des Buches ist seine Aktualität. Rao bezieht sich auf die neuesten Trends und Technologien im Bereich der Datenanalyse und bietet den Lesern wertvolle Einblicke in die aktuellen Entwicklungen in der Branche.

“Natural Language Processing mit PyTorch” ist mehr als nur ein einführendes Buch zum NLP. Es ist ein Leitfaden, der den Lesern hilft, eine datenorientierte Denkweise zu entwickeln und eigentlich ein Verständnis für Sprache aus Sicht eines Data Scientist zu schaffen.

Insgesamt ist “Natural Language Processing mit PyTorch” ein ausgezeichnetes Buch für jeden, der mehr über Datenanalyse lernen möchte. Mit der zunehmenden Menge an Daten, die in der heutigen Welt generiert werden, wird das Verständnis von NLP immer wichtiger. Dieses Buch bietet einen soliden Einstieg in das Thema und ist ein wertvolles Werkzeug für jeden, der in der datenintensiven Welt von heute erfolgreich sein möchte. Es ist ein Muss für jeden, der sich für NLP interessiert und seine Kenntnisse in diesem Bereich erweitern möchte.

[Tianqi (Tessie) Zhao · Rating 4 out of 5]

This book is written by a Ph.D. student from Johns Hopkins, a university that has a lot of famous Natural Language Processing(NLP) experts. The whole book is based on important concepts of NLP, from traditional methods like TF-IDF to neural network-based methods such as Convolutional Neural Networks and Recurrent Neural Networks, and Sequence to Sequence Machine Translation. Each concept is combined with snippets of PyTorch examples coherent to the topic. The whole book is based on several projects, avoiding to change context frequently to make it easy for understanding. As a Computer Science Master who already have publications, I still learned a lot of new things from this book since the author explains every concept in his own words, making it crystal clear, which won’t be possible to achieve without rich hands-on experience. Therefore, though having small mistakes and being lack of specific materials, this book has all the essential knowledge of neural network-based Natural Language Processing and is suitable for readers who has a basic understanding of Artificial Intelligence.

[Manoj Joshi · Rating 1 out of 5]

I was very disappointed. Looks like this book was written in a hurry. The authors assume the readers are at the same level as themselves and will just understand the code they seem to have thrown out arbitrarily. Hardly is there any effort to set the context and help the reader build and develop the concepts from the ground up. In one instance, even the code example and the output did not match when I tried that myself. How could the authors be so careless? Not a book in the O'reilly league.

Sorry folks, but not worth in my opinion.

This is just my perspective though. If others found it useful, I have no comments about that.

[Arie · Rating 4 out of 5]

This book contains great deal of practical codes, from traditional NLP to encoder - decoder attention neural network. However, current NLP advancement has now make use of transformer, which is not this book's scope.

Additionally I've found the Hands On ML by Aurelien Geron provides more in depth discussion on optimization each components of deep learning both for NLP and Vision.

I would recommend to read both books as IMO they can complete each other (despite the intersections that they may have)

[Risto Hinno · Rating 4 out of 5]

Good intro to NLP with pytorch. Easy to read and have real working code examples. So if you want to use pytorch in NLP then this book might be for you. It is not very detailed but gives good idea about different architectures. Companions code was a bit messy I refactored it a bit: https://github.com/RRisto/pytorchnlpbook. But if you want to know state of the art solutions and engineering in NLP you should read some other book after this book.

[Nikhil Prabhu · Rating 3 out of 5]

Great for getting some hands-on practice into actual deep learning and creating models - especially when you try the same models on different datasets and see things break and have to fix them. Besides that, not a very insightful read.

[Juan Manuel · Rating 4 out of 5]

Great book with really up-to-date examples of neural architectures for NLP.

The companion code is a bit messy, though he

[Robin Dong]

Very good book. Easy to understand.

[Romilly · Rating 5 out of 5]

A good introduction to NLP using one of the top two Deep Learning frameworks.