Jump to ratings and reviews
Rate this book

Applied Natural Language Processing with Python: Implementing Machine Learning and Deep Learning Algorithms for Natural Language Processing

Rate this book
Chapter 1: What is Natural Language Processing? Chapter Establishing understanding of topic and give overview of textNo of 10 pagesSub -Topics1. History of Natural Language Processing 2. Word Embeddings3. Neural Networks applied to Natural Language Processing 4. Python Packages

Chapter 2: Review of Machine LearningChapter Discuss models that will be referenced in the textNo of 30 pagesSub - Topics 1. Gradient Descent 2. Multi-Layer Perceptrons 3. Recurrent Neural Networks4. LSTM networks
Chapter 3: Working with Raw Text Chapter Introduce reader to the fundamental aspects of Natural Language Processing that will be utilized more heavily in the chapters regarding No of 30Sub - 1. Word Tokenization 2. Preprocessing and cleaning of text data3. Web crawling w/ SpaCy4. Lemmas, N-grams, and other NATURAL LANGUAGE PROCESSING concepts
Chapter 4: Word Embeddings and their applicationChapter Introduce reader to the use cases for word embeddings and the packages we utilize for themNo of 50 Sub - 1. Word2Vec2. Doc2Vec3. GloVe
Chapter 5: Using Machine Learning w/ Natural language ProcessingChapter Give reader specific walkthroughs of advanced applications of Natural Language Processing using Machine Learning within greater applications (spellcheck and sentiment analysis)No of 501. Tensorflow2. Keras3. Caffe

168 pages, Paperback

Published September 14, 2018

1 person is currently reading
13 people want to read

About the author

Taweh Beysolow II

6 books1 follower

Ratings & Reviews

What do you think?
Rate this book

Friends & Following

Create a free account to discover what your friends think of this book!

Community Reviews

5 stars
1 (16%)
4 stars
1 (16%)
3 stars
1 (16%)
2 stars
2 (33%)
1 star
1 (16%)
Displaying 1 of 1 review
102 reviews
June 25, 2021
As someone who has a MSc in Computer Science with focus on NLP: You will not have the skills to work in an professional NLP environment.

If you want to have a short overview of possible neuronal networks for NLP problems, you could read it. But that is all what you will get from this book.

Some points which annoyed my most while reading it:
- The Python code is horrible, and sometimes wrong.
- It could have been a lot shorter if only the first few lines of "code output" would have been printed - who needs the full list of stopwords of NLTK? If interested you can look it up, the same is for all the endless print statements in ugly format.
- The word "lemma" or "stem" was not mentioned a single time in the book.
- The examples of how the result of the word embedding are random. He didn't add any insight-full examples like "run vs running" (because neither stemming nor lemmatization was applied) or "pretty vs beautiful" (or any other synonyms).
- The "in-depth" explanations to models were not understandable and are probably some rephrasing of the original papers. Hints to the original papers would have been more helpful than his attempts to explain something complicated in a non-complicated way.
Displaying 1 of 1 review

Can't find what you're looking for?

Get help and learn more about the design.