هوش مصنوعی برای .NET: گفتار، زبان و جستجو: ساخت برنامه‌های هوشمند با APIهای خدمات شناختی مایکروسافت

Get introduced to the world of artificial intelligence with this accessible and practical guide. Build applications that make intelligent use of language and user interaction to better compete in today’s marketplace. Discover how your application can deeply understand and interpret content on the web or a user’s machine, intelligently react to direct user interaction through speech or text, or make smart recommendations on products or services that are tailored to each individual user. With Microsoft Cognitive Services, you can do all this and more utilizing a set of easy-to-use APIs that can be consumed on the desktop, web, or mobile devices. Developers normally think of AI implementation as a tough task involving writing complex algorithms. This book aims to remove the anxiety by creating a cognitive application with a few lines of code. There is a wide range of Cognitive Services APIs available. This book focuses on some of the most useful and powerful ways that your application can make intelligent use of language. Artificial Intelligence for .NET: Speech, Language, and Search will show you how you can start building amazing capabilities into your applications today. What You'll Learn: Understand the underpinnings of artificial intelligence through practical examples and scenarios Get started building an AI-based application in Visual Studio Build a text-based conversational interface for direct user interaction Use the Cognitive Services Speech API to recognize and interpret speech Look at different models of language, including natural language processing, and how to apply them in your Visual Studio application Reuse Bing search capabilities to better understand a user’s intention Work with recommendation engines and integrate them into your apps. Read more... Abstract: Get introduced to the world of artificial intelligence with this accessible and practical guide. Build applications that make intelligent use of language and user interaction to better compete in today’s marketplace. Discover how your application can deeply understand and interpret content on the web or a user’s machine, intelligently react to direct user interaction through speech or text, or make smart recommendations on products or services that are tailored to each individual user. With Microsoft Cognitive Services, you can do all this and more utilizing a set of easy-to-use APIs that can be consumed on the desktop, web, or mobile devices. Developers normally think of AI implementation as a tough task involving writing complex algorithms. This book aims to remove the anxiety by creating a cognitive application with a few lines of code. There is a wide range of Cognitive Services APIs available. This book focuses on some of the most useful and powerful ways that your application can make intelligent use of language. Artificial Intelligence for .NET: Speech, Language, and Search will show you how you can start building amazing capabilities into your applications today. What You'll Learn: Understand the underpinnings of artificial intelligence through practical examples and scenarios Get started building an AI-based application in Visual Studio Build a text-based conversational interface for direct user interaction Use the Cognitive Services Speech API to recognize and interpret speech Look at different models of language, including natural language processing, and how to apply them in your Visual Studio application Reuse Bing search capabilities to better understand a user’s intention Work with recommendation engines and integrate them into your apps Contents at a Glance 5 Contents 6 About the Author 14 About the Contributing Author 15 About the Technical Reviewer 16 Acknowledgments 17 Introduction 18 Chapter 1: Getting Started with AI Basics 20 Truth vs. Fiction 21 History and Evolution 22 The Current State of Affairs 23 Commoditization of AI 23 Microsoft and AI 24 Basic Concepts 25 Machine Learning 28 Types of Machine Learning 30 Language 31 Natural Language Understanding 31 Natural Language Processing 31 Speech 32 Speech Recognition 32 Voice Recognition 32 TTS and STT 32 Computer Vision 33 Object Detection 33 Image Recognition 34 Face Recognition 35 Optical Character Recognition 35 Microsoft’s Cognitive Services 36 Vision 37 Speech 37 Language 38 Knowledge 38 Search 39 Recap 40 Chapter 2: Creating an AI-Based Application in Visual Studio 41 Prerequisites for Using Cognitive Services 42 Setting Up the Development Environment 42 Getting an Azure Subscription Key for Cognitive Services 42 Step 1: Set Up an Azure Account 43 Step 2: Create a New Cognitive Services Account 45 Step 3: Get the Subscription Key(s) 47 Testing the API 48 What You Want To Do 49 How To Do It 49 Creating Your First AI-based Application 51 The Code 52 The Walkthrough 54 The Result 56 Making Your Application More Interesting 57 Extracting Text Out of Images 57 The Code 57 The Walkthrough 59 The Result 60 Recap 61 Chapter 3: Building a Conversational User Interface with Microsoft Technologies 62 What Is a Conversational User Interface? 64 A Brief History 64 In the Very Beginning: the Command-Line Interface (CLI) 64 And Then Came the Graphical User Interface 66 And UI Evolved Yet Again: Conversational User Interface 68 AI’s Role in CUI 69 Pitfalls of CUI 70 A Hybrid UI (CUI+GUI) May Be the Future 72 Design Principles 74 Microsoft Bot Framework 75 Creating a CUI Application Using Bot Framework 75 Step 0: Prep Your Development Environment 76 Step 1: Create a New Bot Application Project 77 Step 2: First and Default Messages 77 Step 3: Running, Testing, and Debugging Your Bot 79 Step 3: Appointment Scheduling 82 Step 4: Handling System Messages 85 Next Steps 85 Recap 86 Chapter 4: Using Natural Language Understanding 87 What Is NLU? 88 History of Natural Language Understanding 90 Why Natural Language Is Difficult for Machines to Understand 93 Complexities in Natural Language 93 Statistical Models as a Solution Are Insufficient 95 A Promising Future 96 Language Understanding Intelligent Service (LUIS) 96 Architecture of a LUIS-Based Software Application 97 Behind the Scenes 100 Extensive Training Is the Key 101 Getting an Azure Subscription for LUIS 102 Getting Subscription Keys on Azure Portal 103 Applying Subscription Keys in LUIS 104 Demo: Definition App 105 Notes 108 Recap 108 Chapter 5: Exploring a Cognitive Language Model 109 The Bing Spell Check API 109 What Is It? 111 How To Use It 112 Request 112 Response 114 Integration with LUIS 115 The Text Analytics API 117 Language Detection 118 Request 119 Response 120 Key Phrase Extraction 121 Request 123 Response 124 Sentiment Analysis 124 Request 125 Response 126 Topic Detection 126 Request 127 Response 128 Usage Ideas 129 The Web Language Model (WebLM) API 130 Word Breaking 132 Request 132 Response 132 Joint Probability 133 Request 133 Response 134 Conditional Probability 135 Request 135 Response 136 Next Word Prediction 136 Request 136 Response 137 The Linguistic Analysis API 137 Sentence Separation and Tokenization 138 Request 139 Response 139 Part-of-Speech Tagging 141 Request 142 Response 143 Constituency Parsing 143 Request 145 Response 145 Recap 146 Chapter 6: Consuming and Applying LUIS 147 Planning Your App 147 What Should the Bot Be Able to Do? 148 What Information Does the Bot Need from the User? 148 What Should Be Done in LUIS? 148 What Should Be Done in the Bot Framework? 150 Creating a LUIS App 150 Adding Intents 151 Adding/Labeling Utterances 151 Publishing Your App 153 Adding Entities 155 Simple Entities 157 Composite Entities 158 Hierachical Entities 161 Prebuilt Entities 163 Adding a Phrase List 165 Suggested Next Steps 166 Active Learning Through Suggested Utterances 166 Using LUIS Programmatic API for Automation 167 Integrating LUIS with the Bot Framework 167 Creating a Project in Visual Studio 167 Handling an Entity-less Intent 168 Setting Up Your Bot to Use HealthCheckupDialog 169 Testing the Bot in an Emulator 169 Handling an Entity-Full Intent 170 Handling an Intent with Composite Entities 172 Handling the None Intent 174 Adding Your Bot to Skype 174 Publishing Your Bot 174 Registering Your Bot 175 Recap 176 Chapter 7: Interacting with the Speech API 177 Ways to Interact with Speech 178 The Cognitive Search API 179 Speech Recognition 180 Getting Started 180 Getting the JSON Web Token First 180 The Consume Speech API 182 Speech Synthesis 183 Speech Recognition Internals 186 Custom Speech Service 187 Custom Acoustic Model 187 Custom Language Model 196 Pronunciation Data 198 Custom Speech-to-Text Endpoint 199 Speaker Recognition 201 Speaker Verification vs. Speaker Identification 202 Enrollment-Verification 202 Speaker Verification 205 Enrollment–Identification 206 Speaker Recognition-Identification 207 Operation Status 207 Summary 208 Chapter 8: Applying Search Offerings 209 Search Is Everywhere 209 Pervasive, Predictive, Proactive (The Three Ps of Search) 211 History of Bing 212 What’s So Unique About Bing? 213 Search APIs 213 Bing Autosuggest API 214 How to Consume the Bing Autosuggest API 215 The Bing Image Search API 218 How to Consume the Bing Image Search API 219 Bing News Search API 224 Bing Video Search API 227 How to Consume the Bing Video Search API 228 Bing Web Search API 231 How to Consume the Bing Web Search API 232 Summary 235 Chapter 9: Working with Recommendations 236 Understanding the Basics 237 Frequent Brought Together (FBT) Recommendations 238 Item-to-Item Recommendations 239 Recommendations Based on Past History 239 How Do These Recommendations Work? 240 Recommendation Models and Types 244 Recommendation Build 245 Frequent Brought Together (FBT) Build 249 Ranking Recommendation 251 SAR (Smart Adaptive Recommendations) Build 253 Setting Rules in Build 255 Offline Evaluation 256 Recommendation UI 257 Summary 261 Chapter 10: The Future of AI 262 Why Is AI So Popular? 262 Improved Computing Power 263 Inventions in AI Algorithms 264 Data Is the New Currency 264 Emergence of Cloud Computing 266 Services vs Solutions? 266 Cognitive Categories 267 Challenges and the Future of NLU 267 Challenges and Future of Speech 268 Challenges and the Future of Search 268 Challenges and the Future of Recommendations 269 AI First 270 Intelligent Edge 270 Tasks, not Jobs, Will Be Eliminated 271 So Where Do We Go From Here? 273 Index 275 2017 Get introduced to the world of artificial intelligence with this accessible and practical guide. Build applications that make intelligent use of language and user interaction to better compete in today's marketplace. Discover how your application can deeply understand and interpret content on the web or a user's machine, intelligently react to direct user interaction through speech or text, or make smart recommendations on products or services that are tailored to each individual user. With Microsoft Cognitive Services, you can do all this and more utilizing a set of easy-to-use APIs that can be consumed on the desktop, web, or mobile devices. Developers normally think of AI implementation as a tough task involving writing complex algorithms. This book aims to remove the anxiety by creating a cognitive application with a few lines of code. There is a wide range of Cognitive Services APIs available. This book focuses on some of the most useful and powerful ways that your application can make intelligent use of language. Artificial Intelligence for .NET: Speech, Language, and Search will show you how you can start building amazing capabilities into your applications today. What You'll Learn Understand the underpinnings of artificial intelligence through practical examples and scenarios Get started building an AI-based application in Visual Studio Build a text-based conversational interface for direct user interaction Use the Cognitive Services Speech API to recognize and interpret speech Look at different models of language, including natural language processing, and how to apply them in your Visual Studio application Reuse Bing search capabilities to better understand a user's intention Work with recommendation engines and integrate them into your apps Who This Book Is For Developers working on a range of platforms, from .NET and Windows to mobile devices. Examples are given in C#. No prior experience with AI techniques or theory is required.