What do you think?
Rate this book
Applied Natural Language Processing with Python: Implementing Machine Learning and Deep Learning Algorithms for Natural Language Processing
Learn to harness the power of AI for natural language processing, performing tasks such as spell check, text summarization, document classification, and natural language generation. Along the way, you will learn the skills to implement these methods in larger infrastructures to replace existing code or create new algorithms. Applied Natural Language Processing with Python starts with reviewing the necessary machine learning concepts before moving onto discussing various NLP problems. After reading this book, you will have the skills to apply these concepts in your own professional environment.What You Will Learn Utilize various machine learning and natural language processing libraries such as TensorFlow, Keras, NLTK, and GensimManipulate and preprocess raw text data in formats such as .txt and .pdfStrengthen your skills in data science by learning both the theory and the application of various algorithms Who This Book Is For You should be at least a beginner in ML to get the most out of this text, but you needn’t feel that you need be an expert to understand the content.
180 pages, Kindle Edition
Published September 11, 2018
1 person is currently reading
13 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 of 1 review
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.
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