Hey Cyba : the inner workings of a virtual personal assistant / Steve Young.

Format:

Book

Author/Creator:

Young, Steve, 1951- author.

Language:

English

Subjects (All):

Intelligent personal assistants (Computer software).

Artificial intelligence.

Physical Description:

1 online resource (x, 244 pages) : digital, PDF file(s).

Place of Publication:

Cambridge : Cambridge University Press, 2021.

Summary:

Recent developments in artificial intelligence, especially neural network and deep learning technology, have led to rapidly improving performance in voice assistants such as Siri and Alexa. Over the next few years, capability will continue to improve and become increasingly personalised. Today's voice assistants will evolve into virtual personal assistants firmly embedded within our everyday lives. Told through the view of a fictitious personal assistant called Cyba, this book provides an accessible but detailed overview of how a conversational voice assistant works, especially how it understands spoken language, manages conversations, answers questions and generates responses. Cyba explains through examples and diagrams the neural network technology underlying speech recognition and synthesis, natural language understanding, knowledge representation, conversation management, language translation and chatbot technology. Cyba also explores the implications of this rapidly evolving technology for security, privacy and bias, and gives a glimpse of future developments. Cyba's website can be found at HeyCyba.com.

Contents:

Cover

Half-title

Title page

Copyright information

Contents

Preface

1 May I Introduce Myself?

1.1 What Does a Virtual Personal Assistant Do?

1.2 Some Background History

1.3 My Place of Work

1.4 Privacy and Trust

1.5 My Goal in Life

1.6 How Smart Am I?

2 My Inner Workings

2.1 Anatomy of a Conversation

2.2 My Working Parts

3 How My Brain Works

3.1 Patterns

3.2 Artificial Neural Networks

3.3 Recognising Patterns

3.4 Training a Neural Network

3.5 From Static Patterns to Sequences

3.6 Convolutional Networks

3.7 Scaling-up

4 Knowing What I Know

4.1 My Knowledge Graph

4.2 Nodes and Links

4.3 Intent Graphs and Queries

4.4 Creating and Updating Entities

5 What Did You Say?

5.1 Human Speech Production

5.2 My Artificial Ears

5.3 Why Is Speech Recognition So Hard?

5.4 Capturing the Audio

5.5 From Sounds to Words

5.6 Pay Attention!

5.7 Adding a Language Model

5.8 A Postscript from the Bard ...

6 What Does That Mean?

6.1 Intent Graph Generation and Ranking

6.2 Entity Linking

6.3 Multi-task Classification Using a Shared Encoder

6.4 Character-Based Word Embedding

6.5 Sentence Encoding and Recognition

6.6 Sentence/Intent Graph Matching

6.7 Candidate Ranking

7 What Should I Say Next?

7.1 My Conversation Manager

7.2 Learning a Good Dialogue Policy

7.3 Conversational Memory

7.4 Generating My Response

8 Listen to Me

8.1 From Text to Speech

8.2 Text Processing

8.3 Neural Speech Synthesis

8.4 Setting the Right Tone

8.5 Generating the Waveform

9 How Do You Say That In ... ?

9.1 Transformer Networks

9.2 Using a Transformer Network for Language Translation

9.3 Characters or Words or ...

9.4 Multi-lingual Translation

9.5 Beam Search

9.6 The Limits of Neural Machine Translation

10 Let's Chat.

10.1 My Chatty Responders

10.2 Hand-Crafted Response Generation

10.3 Retrieval-Based Response Generation

10.4 Web-Search Response Generation

10.5 Encoder-Decoder Response Generation

10.6 Selecting the Best Response

10.7 Social Chatbots

11 Can You Trust Me?

11.1 Security

11.2 Privacy

11.3 Bias

11.4 Transparency

11.5 Safety

11.6 Personality

11.7 The Bottom Line

12 When All Is Quiet

12.1 Knowledge Graph Maintenance

12.2 Federated Learning

12.3 Student-Teacher Model Reduction

12.4 End of the Tour

13 Future Upgrades and Beyond

13.1 Personalisation

13.2 Towards Self-Learning

13.3 The Neural-Symbolic Interface

13.4 Commonsense Reasoning and Inference

13.5 Planning

13.6 Super-intelligence?

13.7 Another Day

Glossary

Notes

Index.

Notes:

Title from publisher's bibliographic system (viewed on 26 Mar 2021).

ISBN:

1-108-98266-2

1-108-98314-6

1-108-97671-9

OCLC:

1244535142