Blueprints for text analysis using Python : machine learning-based solutions for common real world (NLP) applications / Jens Albrecht, Sidharth Ramachandran and Christian Winkler.

Format:

Book

Author/Creator:

Albrecht, Jens, author.

Ramachandran, Sidharth, author.

Winkler, Christian, author.

Language:

English

Subjects (All):

Natural language processing (Computer science).

Python (Computer program language).

Machine learning.

Physical Description:

1 online resource (404 pages)

Edition:

1st edition

Place of Publication:

Beijing : O'Reilly, [2021]

System Details:

text file

Summary:

Turning text into valuable information is essential for many businesses looking to gain a competitive advantage. There have been many improvements in natural language processing and users have a lot of options when choosing to work on a problem. However, it’s not always clear which NLP tools or libraries would work for a business use—or which techniques you should use and in what order. This practical book provides theoretical background and real-world case studies with detailed code examples to help developers and data scientists obtain insight from text online. Authors Jens Albrecht, Sidharth Ramachandran, and Christian Winkler use blueprints for text-related problems that apply state-of-the-art machine learning methods in Python. If you have a fundamental understanding of statistics and machine learning along with basic programming experience in Python, you’re ready to get started. You’ll learn how to: Crawl and clean then explore and visualize textual data in different formats Preprocess and vectorize text for machine learning Apply methods for classification, topic analysis, summarization, and knowledge extraction Use semantic word embeddings and deep learning approaches for complex problems Work with Python NLP libraries like spaCy, NLTK, and Gensim in combination with scikit-learn, Pandas, and PyTorch

Contents:

1. Gaining early insights from textual data

2. Extracting textual insights with APIs

3. Scraping websites and extracting data

4. Preparing textual data for statistics and machine learning

5. Feature engineering and syntactic similarity

6. Text classification algorithms

7. How to explain a text classifier

8. Unsupervised methods : topic modeling and clustering

9. Text summarization

10. Exploring semantic relationships with word embeddings

11. Performing sentiment analysis on text data

12. Building a knowledge graph

13. Using text analytics in production.

Notes:

Description based on print version record.

ISBN:

1-4920-7403-9

1-4920-7405-5

1-4920-7407-1