book

Conversational AI with Rasa

Name: Conversational AI with Rasa
ISBN: 9781801077057

by Xiaoquan Kong, Guan Wang

October 2021

Beginner to intermediate

264 pages

5h 2m

English

Packt Publishing

Read now

Unlock full access

Conversational AI with Rasa
ForewordContributorsAbout the authorsAbout the reviewers
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedGet in touchShare your thoughts
Section 1: The Rasa Framework
Chapter 1: Introduction to Chatbots and the Rasa Framework
Technical requirementsWhat is ML?Supervised learning (SL)Stages of machine learningPerformance metricsOverfitting and underfittingTransfer learning (TL)Introduction to Natural Language Processing (NLP)Evolution of modern NLPBasic tasks of NLPChatbot basicsIs a chatbot really necessary?Introduction to chatbot architectureIntroduction to the Rasa frameworkWhy Rasa?System architectureInstalling RasaThe pipeline of a Rasa projectRasa command lineCreating a sample projectSummaryFurther reading
Chapter 2: Natural Language Understanding in Rasa
Technical requirementsThe format of NLU training dataThe intent field – storing NLU samplesThe synonym field – storing synonyms and aliasesThe lookup field – providing extra features by using lookup tablesThe regex field – providing extra features by using regular expressionsUsing regex and lookupOverview of Rasa NLU componentsLanguage model componentsTokenizer componentsFeaturizer componentsEntity extraction componentsIntent classifier componentsHandling frequently asked questions by using a response selectorConfiguring your Rasa NLU via a pipelineWhat is a pipeline?Configuring a pipelineThe output of Rasa NLUThe intent field – the purpose of the user's utteranceThe entities field – key parameters of user's utteranceOther possible fieldsTraining and running Rasa NLUTraining our modelsTesting models from the command lineStarting the Rasa NLU servicePractice – building the NLU part of a medical botWhat are the features of our bot?How can we implement our bot in Rasa?Summary
Chapter 3: Rasa Core
Technical requirementsUnderstanding the universe of your bot (domain)Intents and entitiesSlotsAll possible actions the bot can take (actions)All the predefined replies to users (responses)Configuring sessionsTraining data for dialogue management (stories)User messagesBot actions and eventsAuxiliary features (checkpoints and OR statements)Data augmentation (creating longer stories automatically)Reacting to user input (action)Response actionsForm actionsBuilt-in actionsCustom actionsUnderstanding the memory of your bot (slots)The influences of slots on the conversationSlot typesAutomatic slot fillingSetting initial values for slotsUnderstanding the decision-maker of your bot (policies)Configuring policiesBuilt-in policiesPolicy priorityConnecting with other services via endpointsBuilding custom actions using Rasa SDKInstalling the Rasa SDK packageWriting custom actionsTracker objects (tracking the states of conversations)Event objects (records for changes in conversations)Running custom actionsUsing channels to communicate with instant messaging softwareBuilding a tell-the-time botDefining the features that our bot should provideHow can we implement those features?Training models, serving models, and making inferencesSummary
Section 2: Rasa in Action
Chapter 4: Handling Business Logic
Technical requirementsThe fallback mechanism in RasaHandling fallback in NLUHandling fallback in policyMaking intents trigger actionsTriggering actions by using built-in intentsTriggering actions by using custom intentsUsing forms to complete tasksDefining a formActivating a formExecuting a form taskPractice – building a weather forecast chatbotDesigning the features of this botImplementing the bot step by stepTraining models via the command lineRunning the dialogue systemExtending this projectSummary
Chapter 5: Working with Response Selector to Handle Chitchat and FAQs
Technical requirementsDefining retrieval intents – the questions users want to askDefining responses – the answers to the questionsUpdating the configuration to use ResponseSelectorLearning by doing – building an FAQ botWhat are the features of our bot?How can we implement it?Summary
Chapter 6: Knowledge Base Actions to Handle Question Answering
Technical requirementsWhy do we need knowledge base actions?How do you use knowledge base actions?Creating a knowledge baseCreating a custom knowledge base actionDefining NLU data and stories to perform queries from usersHow do knowledge base actions work?How do you customize knowledge base actions?Modifying ActionQueryKnowledgeBase to customize the behaviorCustomizing InMemoryKnowledgeBaseBuilding your own knowledge baseLearning by doing – building a knowledge-based music query chatbotWhat are the features of our bot?How do we implement the bot?Supporting the Neo4j knowledge baseSummary

Chapter 7: Entity Roles and Groups for Complex Named Entity Recognition
Technical requirementsWhy do we need entity roles and entity groups?Using entity roles to distinguish semantics roles in entities of the same typeUsing entity groups to divide entities into groupsConfiguring Rasa to use entity roles and groupsUpdating the entities setting for roles and groupsUpdating forms and stories for roles and groupsComponents supporting entity roles and entity groupsLearning by doing – building a ticket and drink booking botWhat are the features of our bot?How can we implement it?Summary
Chapter 8: Working Principles and Customization of Rasa
Understanding Rasa's NLU moduleHow does the NLU training work?How does NLU inference work?Understanding how Rasa policies workConverting trackers to training dataHow does policy training work?How does policy inference work?Writing Rasa extensionsWriting pipeline and policy extensionsWriting custom slot typesWriting extensions for other functionalitiesPractice – Creating your own custom English tokenizerSummary
Section 3: Best Practices
Chapter 9: Testing and Production Deployment
Testing Rasa projectsValidating data and storiesEvaluating the NLU performanceEvaluating Dialogue management performanceDeploying your Rasa assistant to productionWhen to deployDeployment optionsModel storageTracker storesLock storesHigh-performance settings for Rasa servers and action serversSummary
Chapter 10: Conversation-Driven Development and Interactive Learning
Introduction to CDDIntroduction to Rasa XInstalling Rasa XUsing Rasa XPerforming interactive learningSaving the interactive learning data and exitingSummary
Chapter 11: Debugging, Optimization, and Community Ecosystem
Debugging Rasa systemsWrong prediction of resultsCode errorsOptimizing Rasa systemsUnderstanding the community ecosystem of RasaData generation tool – ChatitoData generation tool – ChatetteData labeling tool – DoccanoLanguage-specific librariesSummary
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare your thoughts

Content preview from Conversational AI with Rasa

Chapter 2: Natural Language Understanding in Rasa

In this chapter, we introduce how to implement Natural Language Understanding (NLU) in Rasa.

Rasa NLU is responsible for intent recognition and entity extraction. For example, if the user input is What's the weather like tomorrow in New York?, Rasa NLU needs to extract that the intent of the user is asking for weather, and the corresponding entity names and type, for example, the date is tomorrow, and the location is New York.

Rasa NLU uses supervised learning algorithms to fulfill this function. A proper number of examples including intent and entity information are needed for training the NLU model. Rasa NLU has a very flexible software architecture design and supports various kinds of algorithms. ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781801077057

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Conversational AI with Rasa

by Xiaoquan Kong, Guan Wang

Chapter 2: Natural Language Understanding in Rasa

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.