Book Image

Machine Learning Techniques for Text

By : Nikos Tsourakis
Book Image

Machine Learning Techniques for Text

By: Nikos Tsourakis

Overview of this book

With the ever-increasing demand for machine learning and programming professionals, it's prime time to invest in the field. This book will help you in this endeavor, focusing specifically on text data and human language by steering a middle path among the various textbooks that present complicated theoretical concepts or focus disproportionately on Python code. A good metaphor this work builds upon is the relationship between an experienced craftsperson and their trainee. Based on the current problem, the former picks a tool from the toolbox, explains its utility, and puts it into action. This approach will help you to identify at least one practical use for each method or technique presented. The content unfolds in ten chapters, each discussing one specific case study. For this reason, the book is solution-oriented. It's accompanied by Python code in the form of Jupyter notebooks to help you obtain hands-on experience. A recurring pattern in the chapters of this book is helping you get some intuition on the data and then implement and contrast various solutions. By the end of this book, you'll be able to understand and apply various techniques with Python for text preprocessing, text representation, dimensionality reduction, machine learning, language modeling, visualization, and evaluation.

Related Content you might be interested in

Current Title:

Small book image
Machine Learning Techniques for Text
Nikos Tsourakis
Oct, 2022 | 448 pages
Small book image
Advanced Natural Language Processing with TensorFlow 2
Ashish Bansal
Feb, 2021 | 380 pages
Small book image
Mastering Transformers
Meysam Asgari Chenaghlu | Savaş Yıldırım
Sep, 2021 | 374 pages
Small book image
Natural Language Understanding with Python
Deborah A Dahl
Jun, 2023 | 326 pages
Table of Contents (13 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code files
Conventions used
Get in touch
Share Your Thoughts
Download a free PDF copy of this book
1
Chapter 1: Introducing Machine Learning for Text
Chapter 1: Introducing Machine Learning for Text
The language phenomenon
The data explosion
The era of AI
Relevant research fields
The machine learning paradigm
Taxonomy of machine learning techniques
Visualization of the data
Evaluation of the results
Summary
Free Chapter
2
Chapter 2: Detecting Spam Emails
Chapter 2: Detecting Spam Emails
Technical requirements
Understanding spam detection
Extracting word representations
Executing data preprocessing
Performing classification
Measuring classification performance
Summary
3
Chapter 3: Classifying Topics of Newsgroup Posts
Chapter 3: Classifying Topics of Newsgroup Posts
Technical requirements
Understanding topic classification
Performing exploratory data analysis
Executing dimensionality reduction
Introducing the k-nearest neighbors algorithm
Introducing the random forest algorithm
Extracting word embedding representation
Summary
4
Chapter 4: Extracting Sentiments from Product Reviews
Chapter 4: Extracting Sentiments from Product Reviews
Technical requirements
Understanding sentiment analysis
Performing exploratory data analysis
Introducing linear regression
Introducing logistic regression
Introducing deep neural networks
Summary
5
Chapter 5: Recommending Music Titles
Chapter 5: Recommending Music Titles
Technical requirements
Understanding recommender systems
Performing exploratory data analysis
Introducing content-based filtering
Introducing collaborative filtering
Summary
6
Chapter 6: Teaching Machines to Translate
Chapter 6: Teaching Machines to Translate
Technical requirements
Understanding machine translation
Introducing rule-based machine translation
Introducing example-based machine translation
Introducing statistical machine translation
Introducing sequence-to-sequence learning
Measuring translation performance
Summary
7
Chapter 7: Summarizing Wikipedia Articles
Chapter 7: Summarizing Wikipedia Articles
Technical requirements
Understanding text summarization
Introducing web scraping
Performing extractive summarization
Performing abstractive summarization
Measuring summarization performance
Summary
8
Chapter 8: Detecting Hateful and Offensive Language
Chapter 8: Detecting Hateful and Offensive Language
Technical requirements
Introducing social networks
Understanding BERT
Introducing boosting algorithms
Creating validation sets
Treating imbalanced datasets
Classifying with BERT
Understanding CNN
Summary
9
Chapter 9: Generating Text in Chatbots
Chapter 9: Generating Text in Chatbots
Technical requirements
Understanding text generation
Creating a retrieval-based chatbot
Understanding language modeling
Creating a generative chatbot
Summary
10
Chapter 10: Clustering Speech-to-Text Transcriptions
Chapter 10: Clustering Speech-to-Text Transcriptions
Technical requirements
Understanding text clustering
Preprocessing the data
Using speech-to-text
Introducing the K-means algorithm
Introducing DBSCAN
Introducing the hierarchical clustering algorithm
Introducing the LDA algorithm
Summary
11
Index
Index
Why subscribe?
12
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share Your Thoughts
Download a free PDF copy of this book

Understanding recommender systems

In an ever-growing digital world, customers are often overwhelmed by the choices available and need assistance finding what they want. It comes as no surprise that their habits and preferences are valuable assets to overcome this hurdle. Both assist in identifying user needs and permit companies to promote new products and services at the right time and place. Nonetheless, with most of the services being predominately online, having direct access to your customers is challenging. So, what is the solution?

Let’s consider a few standard user inputs to answer this question, such as the number of stars awarded in an Amazon book review. Ratings provide a quality measure for the items in any online store. Similarly, the view count of a YouTube video is an engagement metric that can be used to recommend the same video to others. The number of views is an implicit indicator while rating scores are explicit. In both cases, however, an automatic system...

Previous Section
End of Section 3
Next Section