Book Image

Natural Language Understanding with Python

By : Deborah A. Dahl
5 (1)
Book Image

Natural Language Understanding with Python

5 (1)
By: Deborah A. Dahl

Overview of this book

Natural Language Understanding facilitates the organization and structuring of language allowing computer systems to effectively process textual information for various practical applications. Natural Language Understanding with Python will help you explore practical techniques for harnessing NLU to create diverse applications. with step-by-step explanations of essential concepts and practical examples, you’ll begin by learning about NLU and its applications. You’ll then explore a wide range of current NLU techniques and their most appropriate use-case. In the process, you’ll be introduced to the most useful Python NLU libraries. Not only will you learn the basics of NLU, you’ll also discover practical issues such as acquiring data, evaluating systems, and deploying NLU applications along with their solutions. The book is a comprehensive guide that’ll help you explore techniques and resources that can be used for different applications in the future. By the end of this book, you’ll be well-versed with the concepts of natural language understanding, deep learning, and large language models (LLMs) for building various AI-based applications.

Related Content you might be interested in

Current Title:

Small book image
Natural Language Understanding with Python
Deborah A. Dahl
Jun, 2023 | 326 pages
Small book image
Mastering spaCy
Duygu Altınok
Jul, 2021 | 356 pages
Small book image
Hands-On Python Natural Language Processing
Mayank Rasu | Aman Kedia
Jun, 2020 | 316 pages
Small book image
The Handbook of NLP with Gensim
Chris Kuo
Oct, 2023 | 310 pages
Table of Contents (21 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
Download the color images
Conventions used
Get in touch
Share your thoughts
Download a free PDF copy of this book
1
Part 1: Getting Started with Natural Language Understanding Technology
Part 1: Getting Started with Natural Language Understanding Technology
Free Chapter
2
Chapter 1: Natural Language Understanding, Related Technologies, and Natural Language Applications
Chapter 1: Natural Language Understanding, Related Technologies, and Natural Language Applications
Understanding the basics of natural language
Global considerations – languages, encodings, and translations
The relationship between conversational AI and NLP
Exploring interactive applications – chatbots and voice assistants
Exploring non-interactive applications
A look ahead – Python for NLP
Summary
3
Chapter 2: Identifying Practical Natural Language Understanding Problems
Chapter 2: Identifying Practical Natural Language Understanding Problems
Identifying problems that are the appropriate level of difficulty for the technology
Taking development costs into account
Taking maintenance costs into account
A flowchart for deciding on NLU applications
Summary
4
Part 2:Developing and Testing Natural Language Understanding Systems
Part 2:Developing and Testing Natural Language Understanding Systems
5
Chapter 3: Approaches to Natural Language Understanding – Rule-Based Systems, Machine Learning, and Deep Learning
Chapter 3: Approaches to Natural Language Understanding – Rule-Based Systems, Machine Learning, and Deep Learning
Rule-based approaches
Traditional machine learning approaches
Deep learning approaches
Pre-trained models
Considerations for selecting technologies
Summary
6
Chapter 4: Selecting Libraries and Tools for Natural Language Understanding
Chapter 4: Selecting Libraries and Tools for Natural Language Understanding
Technical requirements
Installing Python
Developing software – JupyterLab and GitHub
Exploring the libraries
Looking at an example
Summary
7
Chapter 5: Natural Language Data – Finding and Preparing Data
Chapter 5: Natural Language Data – Finding and Preparing Data
Finding sources of data and annotating it
Ensuring privacy and observing ethical considerations
Preprocessing data
Application-specific types of preprocessing
Choosing among preprocessing techniques
Summary
8
Chapter 6: Exploring and Visualizing Data
Chapter 6: Exploring and Visualizing Data
Why visualize?
Data exploration
General considerations for developing visualizations
Using information from visualization to make decisions about processing
Summary
9
Chapter 7: Selecting Approaches and Representing Data
Chapter 7: Selecting Approaches and Representing Data
Selecting NLP approaches
Representing language for NLP applications
Representing language numerically with vectors
Representing words with context-independent vectors
Representing words with context-dependent vectors
Summary
10
Chapter 8: Rule-Based Techniques
Chapter 8: Rule-Based Techniques
Rule-based techniques
Why use rules?
Exploring regular expressions
Word-level analysis
Sentence-level analysis
Summary
11
Chapter 9: Machine Learning Part 1 – Statistical Machine Learning
Chapter 9: Machine Learning Part 1 – Statistical Machine Learning
A quick overview of evaluation
Representing documents with TF-IDF and classifying with Naïve Bayes
Classifying documents with Support Vector Machines (SVMs)
Slot-filling with CRFs
Summary
12
Chapter 10: Machine Learning Part 2 – Neural Networks and Deep Learning Techniques
Chapter 10: Machine Learning Part 2 – Neural Networks and Deep Learning Techniques
Basics of NNs
Example – MLP for classification
Hyperparameters and tuning
Moving beyond MLPs – RNNs
Looking at another approach – CNNs
Summary
13
Chapter 11: Machine Learning Part 3 – Transformers and Large Language Models
Chapter 11: Machine Learning Part 3 – Transformers and Large Language Models
Technical requirements
Overview of transformers and LLMs
BERT and its variants
Using BERT – a classification example
Cloud-based LLMs
Summary
14
Chapter 12: Applying Unsupervised Learning Approaches
Chapter 12: Applying Unsupervised Learning Approaches
What is unsupervised learning?
Topic modeling using clustering techniques and label derivation
Making the most of data with weak supervision
Summary
15
Chapter 13: How Well Does It Work? – Evaluation
Chapter 13: How Well Does It Work? – Evaluation
Why evaluate an NLU system?
Evaluation paradigms
Data partitioning
Evaluation metrics
User testing
Statistical significance of differences
Comparing three text classification methods
Summary
16
Part 3: Systems in Action – Applying Natural Language Understanding at Scale
Part 3: Systems in Action – Applying Natural Language Understanding at Scale
17
Chapter 14: What to Do If the System Isn’t Working
Chapter 14: What to Do If the System Isn’t Working
Technical requirements
Figuring out that a system isn’t working
Fixing accuracy problems
Moving on to deployment
Problems after deployment
Summary
18
Chapter 15: Summary and Looking to the Future
Chapter 15: Summary and Looking to the Future
Overview of the book
Potential for improvement – better accuracy and faster training
Applications that are beyond the current state of the art
Future directions in NLU technology and research
Summary
Further reading
19
Index
Index
Why subscribe?
20
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

Potential for improvement – better accuracy and faster training

At the beginning of Chapter 13, we listed several criteria that can be used to evaluate NLU systems. The one that we usually think of first is accuracy – that is, given a specific input, did the system provide the right answer? Although in a particular application, we eventually may decide to give another criterion priority over accuracy, accuracy is essential.

Better accuracy

As we saw in Chapter 13, even our best-performing system, the large Bidirectional Encoder Representations from Transformers (BERT) model, only achieved an F1 score of 0.85 on the movie review dataset, meaning that 15% of its classifications were incorrect. State-of-the-art LLM-based research systems currently report an accuracy of 0.93 on this dataset, which still means that the system makes many errors (SiYu Ding, Junyuan Shang, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2021. ERNIE-Doc: A Retrospective Long-Document...

Previous Section
End of Section 3
Next Section