book

Getting Started with Artificial Intelligence, 2nd Edition

by Tom Markiewicz, Josh Zheng

October 2020

Beginner

83 pages

1h 55m

English

O'Reilly Media, Inc.

Read now

Unlock full access

The Market for Artificial IntelligenceAvoiding an AI WinterArtificial Intelligence, Defined?Artificial IntelligenceMachine LearningDeep LearningApplications in the EnterpriseNext Steps
Overview of NLPThe Components of NLPEntitiesRelationsConceptsKeywordsSemantic RolesCategoriesEmotionSentimentEnterprise Applications of NLPSocial Media AnalysisCustomer SupportBusiness IntelligenceContent Marketing and RecommendationAdditional TopicsHow to Use NLPTraining ModelsChallenges of NLPSummary
What Is a Chatbot?The Rise of ChatbotsNatural Language Processing in the CloudProliferation of Messaging PlatformsNatural Language InterfaceHow to Build a ChatbotThe Messaging ChannelThe BackendChallenges of Building a Successful ChatbotSummary
Capabilities of Computer Vision for the EnterpriseImage Classification and TaggingObject LocalizationCustom ClassifiersHow to Use Computer VisionComputer Vision on Mobile DevicesBest PracticesQuality Training ImagesUse CasesSatellite ImagingVideo Search in Surveillance and EntertainmentAdditional Examples: Social Media and InsuranceExisting Challenges in Computer VisionImplementing a Computer Vision SolutionSummary
Preparing for a Data PipelineSourcing Big DataStorage: Apache HadoopHadoop as a Data LakeDiscovery: Apache SparkSpark Versus MapReduceMachine Learning with SparkAutomationWhy Automated AI/ML?Limitations of AutoMLExisting Automated Machine Learning SolutionsSummary
Overview of CloudsConcerns about the CloudPublic and PrivateHybridMulticloudCloud ConstructionUsing AI on Hybrid CloudsPrivacy and SecurityPortability and ScalabilityProcessing and Computing PowerExample of AI on Hybrid CloudsPractical SolutionsThe Future of AI on Hybrid CloudsSummary
What Makes Enterprises Unique?Current Challenges, Trends, and OpportunitiesLittle DataInaccessible Data FormatsEnsuring Accountability and InterpretabilityFairness, Trust, and TransparencyScalabilitySocial ImplicationsSummary

Content preview from Getting Started with Artificial Intelligence, 2nd Edition

Chapter 3. Chatbots

AI is a tool. The choice about how it gets deployed is ours.

Oren Etzioni, professor, University of Washington

Dr. Ashok Goel teaches a class called Knowledge-Based Artificial Intelligence every semester at Georgia Tech. It’s a massive class of around 300 registered students. Understandably, being a teaching assistant (TA) for this course can be quite the challenge as 300 students post roughly 10,000 messages in the online forums. But during the spring semester of 2017, one particular TA was especially good at her job. She answered the students’ questions with excellent efficiency. She would even make herself available during late hours the night before a deadline. Naturally, the students loved her and gave her rave reviews.

You can probably guess how the story ends. At the end of the semester, most students were surprised to find out that the TA, named Jill Watson, was actually a chatbot. Dr. Goel and his team built Jill by tracking down all the questions that had ever been asked on the course’s online forum (about 40,000 postings in all). They then trained Jill to answer these questions using IBM Watson. Jill wasn’t very good at first, but she learned from her mistakes and was eventually giving answers with 97% certainty.

It’s stories like this that sparked the interest of developers and entrepreneurs and fueled interest in chatbots. In this chapter, we will explore a few aspects of this topic. We’ll talk about what a chatbot is, why now is an excellent ...