@Ditatoo1 #LavaCon
Writing for Chatbots
Presenter: Alex Masycheff, CEO, Intuillion
@Ditatoo1 #LavaCon
“Writing” means designing knowledge and
representing it in a way that makes the
knowledge discoverable by chatbots and
helpful for users.
@Ditatoo1 #LavaCon
Goal: to learn how to build information
infrastructure for a chatbot solution.
@Ditatoo1 #LavaCon
We will:
• Create taxonomies
• Create ontologies
• Work with metadata
• Design content architecture
@Ditatoo1 #LavaCon
We will have to understand the underlying
technology.
@Ditatoo1 #LavaCon
A chatbot should provide an additional value.
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
What the Chatbot Should Be Able to Do
1 Identify the intent (what the user wants)
2 Identify missing information
3 Ask questions to gather the missing information
(but not too many!)
4 Find the right content
@Ditatoo1 #LavaCon
What the Chatbot Should Be Able to Do
1 Identify the intent (what the user wants)
2 Identify missing information
3 Ask questions to gather the missing information
(but not too many!)
4 Find the right content
@Ditatoo1 #LavaCon
Getting Request from the User
@Ditatoo1 #LavaCon
Getting Request from the User
@Ditatoo1 #LavaCon
Getting Request from the User
Pre-defined buttons
Easy to implement
Easy to interpret user’s answer
@Ditatoo1 #LavaCon
Getting Request from the User
Pre-defined buttons
Easy to implement
Easy to interpret user’s answer
Hard to scale
May be hard to fit the user’s mindset
@Ditatoo1 #LavaCon
Getting Request from the User
Free text
Easier for the user
Scalable
Hard to understand
Error prone and brittle
@Ditatoo1 #LavaCon
Recognizing Intents in Free Text
Connecting the printer to a computer
Loading paper
Printing a document
Replacing the cartridge
Pre-Defined Intents
Scanning a document
…
@Ditatoo1 #LavaCon
Recognizing Intents in Free Text
Connecting the printer to a computer
Loading paper
Printing a document
Replacing the cartridge
Pre-Defined Intents
Scanning a document
…
User’s Question
How to replace the cartridge?
@Ditatoo1 #LavaCon
Recognizing Intents in Free Text
Connecting the printer to a computer
Loading paper
Printing a document
Replacing the cartridge
Pre-Defined Intents
Scanning a document
…
User’s Question
How to replace the cartridge?
Natural Language
Understanding Engine
Rasa
Watson
LUIS
DialogFlow
…
@Ditatoo1 #LavaCon
Recognizing Intents in Free Text
Connecting the printer to a computer
Loading paper
Printing a document
Replacing the cartridge
Pre-Defined Intents
Scanning a document
…
User’s Question
How to replace the cartridge?
Natural Language
Understanding Engine
Rasa
Watson
LUIS
DialogFlow
…
@Ditatoo1 #LavaCon
Utterance-Based Intent Recognition
Replacing the cartridge
How to replace a cartridge?
What should I do replace a cartridge?
What it takes to replace a cartridge?
What are the steps for putting a new
cartridge instead of the old one?
…
Utterances:
=
@Ditatoo1 #LavaCon
Machine Learning for Intent Recognition
Manually defined utterances
User’s questions automatically
mapped to the intent
“A real-world app should have at least 15 utterances of varying length, word order, tense,
grammatical correctness, punctuation, and word count. “ (LUIS Documentation)
@Ditatoo1 #LavaCon
Exercise
Identify a few intents and a few utterances for each intent
for your products
@Ditatoo1 #LavaCon
What the Chatbot Should Be Able to Do
1 Identify the intent (what the user wants)
2 Identify missing information
3 Ask questions to gather the missing information
(but not too many!)
4 Find the right content
@Ditatoo1 #LavaCon
Request with Missing Information
How to replace a cartridge?
@Ditatoo1 #LavaCon
Request with Missing Information
In which model?
Color or black-and-white?
How to replace a cartridge?
@Ditatoo1 #LavaCon
Complete Request
How to replace a color cartridge in All-In-One?
@Ditatoo1 #LavaCon
Entities Are Initially Labelled Manually
@Ditatoo1 #LavaCon
Entities Are Initially Labelled Manually
“Entities need many examples in order to have a high confidence of prediction. ”
(LUIS Documentation)
@Ditatoo1 #LavaCon
What the Chatbot Should Be Able to Do
1 Identify the intent (what the user wants)
2 Identify missing information
3 Ask questions to gather the missing information
(but not too many!)
4 Find the right content
@Ditatoo1 #LavaCon
Incomplete Request
How to replace a color cartridge? ?
@Ditatoo1 #LavaCon
Filling Out Slots
In which model?
How to replace a color cartridge? ?
@Ditatoo1 #LavaCon
Filling Out Slots
Color or black-and-white?
How to replace a cartridge in Pro??
@Ditatoo1 #LavaCon
Combinatorial Explosion
• Entities may depend on previous intents
• Entities may also depend on previous user’s answers
• Amount of combinations might be enormous
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Printing Printing
Scanning
Printing
Scanning
Faxing
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Learn about featuresIntent
Entities Model Name
Printing Printing
Scanning
Printing
Scanning
Faxing
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Learn about featuresIntent
Entities Model Name
Printing Printing
Scanning
Printing
Scanning
Faxing
What features does EasyPrint All-In-One have?
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Learn about featuresIntent
Entities Model Name
Printing Printing
Scanning
Printing
Scanning
Faxing
What features does EasyPrint All-In-One have?
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Learn about featuresIntent
Entities Model Name
Printing Printing
Scanning
Printing
Scanning
Faxing
Which models can send and receive faxes?
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Learn about featuresIntent
Entities Model Name
Printing Printing
Scanning
Printing
Scanning
Faxing
Which models can send and receive faxes?
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-One
Cable
Wi-Fi
Check the cable
Check the Wi-Fi connection
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-One
Fix “doesn’t print” issueIntent
Entities Model Name
Cable
Wi-Fi
ConnectivityMethod
Check the cable
Check the Wi-Fi connection
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-One
Fix “doesn’t print” issueIntent
Entities Model Name
Cable
Wi-Fi
My printer doesn’t print anything
ConnectivityMethod
Check the cable
Check the Wi-Fi connection
@Ditatoo1 #LavaCon
Only One Perspective
EasyPrint All-In-One
Fix “doesn’t print” issueIntent
Entities Model Name
Cable
Wi-Fi
The printer’s cable is broken. How will it affect
the printer?
ConnectivityMethod
Check the cable
Check the Wi-Fi connection
@Ditatoo1 #LavaCon
Exercise
Identify a few entities for a few intents for your products
@Ditatoo1 #LavaCon
When It Works
• Small amount of content
• The amount of content isn’t growing
• No or few content variations
• Conversations with the user are simple and
straightforward
@Ditatoo1 #LavaCon
“Today many programs do outstanding jobs more efficiently and reliably. Some of them
can beat people at chess. Others can diagnose heart attacks. Yet others can recognize
pictures of faces, assemble cars in factories, or even pilot planes or ships. But no machine
yet can read a book, clean a house, or baby-sit.
Then why cannot our computers yet do so many things that people can do? Do they need
more memory, speed, or complexity? Or do machines lack some magical attribute that
only a human brain can possess?
One of these limitations is that we usually give a present-day program only the knowledge
we think it will need to solve each particular problem. In contrast, every normal child
learns millions of fragments of knowledge and skills that people regard as “obvious.””
Marvin Minsky, The Emotion Machine
@Ditatoo1 #LavaCon
Navigation Map
@Ditatoo1 #LavaCon
Navigation Map + User’s Input
Current location: Amsterdam
Destination: Breda
Avoid toll roads
@Ditatoo1 #LavaCon
Navigation Map + User’s Input
Current location: Amsterdam
Destination: Breda
Avoid toll roads
OntologyUser’s Context
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
API
Chatbots
Knowledge Bases
Linkage
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
APILinkage
@Ditatoo1 #LavaCon
Taxonomy
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues Order
Cartridge
Toner
Paper
@Ditatoo1 #LavaCon
Taxonomy’s Purpose
• Who will use it?
• How will they use it?
• What information should be provided?
@Ditatoo1 #LavaCon
Taxonomy Examples: Aircraft Manufacturer
Systems
Air conditioning & pressurization
Communications
APU
COCKPIT EMER ACCESS
BAGGAGE DOOR OPN
AVIONICS NOT CLSD
Fuel
E1 FUEL LO PRESS
HI TEMP
IMBALANCE
Doors
@Ditatoo1 #LavaCon
Taxonomy Examples: Aircraft Manufacturer
Systems
Air conditioning & pressurization
Communications
APU
COCKPIT EMER ACCESS
BAGGAGE DOOR OPN
AVIONICS NOT CLSD
Fuel
E1 FUEL LO PRESS
HI TEMP
IMBALANCE
Doors
@Ditatoo1 #LavaCon
Taxonomy Examples: Aircraft Manufacturer
Systems
Air conditioning & pressurization
Communications
APU
COCKPIT EMER ACCESS
BAGGAGE DOOR OPN
AVIONICS NOT CLSD
Fuel
E1 FUEL LO PRESS
HI TEMP
IMBALANCE
Doors
Emergency Procedures
@Ditatoo1 #LavaCon
Taxonomy Examples: Aircraft Manufacturer
Systems
Air conditioning & pressurization
Communications
APU
COCKPIT EMER ACCESS
BAGGAGE DOOR OPN
AVIONICS NOT CLSD
Fuel
E1 FUEL LO PRESS
HI TEMP
IMBALANCE
Doors
@Ditatoo1 #LavaCon
Taxonomy Examples: Aircraft Manufacturer
Systems
Air conditioning & pressurization
Communications
APU
COCKPIT EMER ACCESS
BAGGAGE DOOR OPN
AVIONICS NOT CLSD
Fuel
E1 FUEL LO PRESS
HI TEMP
IMBALANCE
Doors
@Ditatoo1 #LavaCon
Taxonomy Examples: Aircraft Manufacturer
Systems
Air conditioning & pressurization
Communications
APU
COCKPIT EMER ACCESS
BAGGAGE DOOR OPN
AVIONICS NOT CLSD
Fuel
E1 FUEL LO PRESS
HI TEMP
IMBALANCE
Doors
@Ditatoo1 #LavaCon
Taxonomy Example: Electricity Distributor
Products
Charging Equipment
Smart Grid
Grid Automation
Transformer Substations
Projects
Project 1
Project 2
Project 3
Locale
Europe
North America
Applications
Horticulture
Street lights
Active Load Balancing
Audience
Internal
Installer
Operator
Sales
Service Maintenance
@Ditatoo1 #LavaCon
Taxonomy Example: Electricity Distributor
Products
Charging Equipment
Smart Grid
Grid Automation
Transformer Substations
Projects
Project 1
Project 2
Project 3
Locale
Europe
North America
Applications
Horticulture
Street lights
Active Load Balancing
Audience
Internal
Installer
Operator
Sales
Service Maintenance
Publishing
engine
@Ditatoo1 #LavaCon
Exercise
Create a taxonomy for your products
@Ditatoo1 #LavaCon
What Taxonomy Doesn’t Tell
Products
Charging Equipment
Smart Grid
Grid Automation
Transformer Substations
Projects
Project 1
Project 2
Project 3
Locale
Europe
North America
What products are involved in Project 1?
In what projects a specific product is involved?
Are projects region-specific?
What characteristics should an activity have to
be defined as project?
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
APILinkage
@Ditatoo1 #LavaCon
Semantic Relationships
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Semantic Relationships
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Semantic Relationships
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Semantic Relationships
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Semantic Relationships
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Semantic Relationships
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Crawling the Ontology
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Crawling the Ontology
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues
is of typehas connectivity
might be caused by
might have issues
Order
Cartridge
Toner
Paper
can order
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
@Ditatoo1 #LavaCon
Relationship’s Purpose
• Who and what will use it?
• How will it be used?
• What information should be discovered?
@Ditatoo1 #LavaCon
Exercise
Add semantic relationships to your taxonomy
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
APILinkage
@Ditatoo1 #LavaCon
Semantic Relationships
Printers
Laser
Inkjet
EasyPrint All-In-One
EasyPrint Pro
EasyPrint Basic
Scanning
Faxing
Printing
Features
Copying
Issues
Toner
Cartridge
Connectivity
No ink
Ink leakage
No ink
Ink leakage
Wi-Fi
Wi-Fi
Cable
No network
Wrong IP address
Connector broken
USB port broken
Antenna broken
has feature
@Ditatoo1 #LavaCon
Rule
Printers
Laser
Inkjet
EasyPrint All-In-One
EasyPrint Pro
EasyPrint Basic
Scanning
Faxing
Printing
Features
Copying
Issues
Toner
Cartridge
Connectivity
No ink
Ink leakage
No ink
Ink leakage
Wi-Fi
Wi-Fi
Cable
No network
Wrong IP address
Connector broken
USB port broken
Antenna broken
has feature
If X has feature F,
and feature F
might have issue I
-> X might have
issue I
@Ditatoo1 #LavaCon
Semantic Relationships
EasyPrint All-In-One
Doesn’t Print
has issue
Wi Fi
has feature
Enabled
is in state
@Ditatoo1 #LavaCon
Rule
EasyPrint All-In-One
Doesn’t Print
has issue
Wi Fi
has feature
Enabled
is in state
If X has problem P, and X has
features F1 and F2, and feature
F1 has relationship R to feature
F2 -> the cause of the problem
is C.
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
APILinkage
@Ditatoo1 #LavaCon
Inference
Printers
Laser
Inkjet
EasyPrint All-In-One
EasyPrint Pro
EasyPrint Basic
Scanning
Faxing
Printing
Features
Copying
Issues
Toner
Cartridge
Connectivity
No ink
Ink leakage
No ink
Ink leakage
Wi-Fi
Wi-Fi
Cable
No network
Wrong IP address
Connector broken
USB port broken
Antenna broken
@Ditatoo1 #LavaCon
Inference
EasyPrint All-In-One
Doesn’t Print
has issue
Wi Fi
has feature
Enabled
is in state
Printer driver stopped
@Ditatoo1 #LavaCon
Inference
• Produces new information
• Doesn’t require to foresee all possible combinations
• May reduce the amount of questions to ask the user
• Enables multiple perspectives
@Ditatoo1 #LavaCon
Only One Perspective without Ontology
EasyPrint All-In-OneEasyPrint ProEasyPrint Basic
Learn about featuresIntent
Entities Model Name
Printing Printing
Scanning
Printing
Scanning
Faxing
What features does EasyPrint All-In-One have?
@Ditatoo1 #LavaCon
Multiple Perspectives with Ontology
Printers
Laser
Inkjet
EasyPrint All-In-One
EasyPrint Pro
EasyPrint Basic
Scanning
Faxing
Printing
Features
Copying
Issues
Toner
Cartridge
Connectivity
No ink
Ink leakage
No ink
Ink leakage
Wi-Fi
Wi-Fi
Cable
No network
Wrong IP address
Connector broken
USB port broken
Antenna broken
has feature
@Ditatoo1 #LavaCon
Exercise
Create rules for your ontology
@Ditatoo1 #LavaCon
What the Chatbot Should Be Able to Do
1 Identify the intent (what the user wants)
2 Identify missing information
3 Ask questions to gather the missing information
(but not too many!)
4 Find the right content
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
APILinkage
@Ditatoo1 #LavaCon
User’s Context Elements
Issue
Connectivity Type
Product Model
@Ditatoo1 #LavaCon
Combinations of User’s Context Elements
BasicModel Pro
CableConnectivity Wi-Fi
Issue
Doesn’t
print
Paper jam Light print
All-In-One
@Ditatoo1 #LavaCon
Combinations of User’s Context Elements
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue Doesn’t
print
Paper jam Light print
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue
Doesn’t
print
Paper jam Light print
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue Doesn’t
print
Paper jam Light print
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue Doesn’t
print
Paper jam Light print
@Ditatoo1 #LavaCon
Granular (Structured) Content
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue Doesn’t
print
Paper jam Light print
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue
Doesn’t
print
Paper jam Light print
BasicModel Pro All-In-One
CableConnectivity Wi-Fi
Issue Doesn’t
print
Paper jam Light print
Model: All-In-One
Connectivity: Cable
Issue: Doesn’t print
Model: All-In-One
Connectivity: Wi-Fi
Issue: Doesn’t print
Model: Pro
Connectivity: Cable
Issue: Paper jam
Model: Basic
Connectivity: Cable
Issue: Light print
@Ditatoo1 #LavaCon
Connecting Content to Ontology
Basic
Pro
All-In-One
Model
Ink-jet
Laser
Type
Wi-Fi
Cable
Connectivity
Doesn’t print
Paper jam
Light print
Issues Order
Cartridge
Toner
Paper
@Ditatoo1 #LavaCon
Conversation with a Support Chatbot
Model: All-In-One
Connectivity: Wi-Fi
Issue: Doesn’t print
@Ditatoo1 #LavaCon
Making Suggestions
Printers
Laser
Inkjet
EasyPrint All-In-One
EasyPrint Pro
EasyPrint Basic
Scanning
Faxing
Printing
Features
Copying
Training
Printing
Scanning
Basics Video
Advanced Printing
How to Scan
Scanning Tips
Wi-FiTechpubs dept.
Training dept.
Legal
Regulations
compliant with
Compliance dept.
@Ditatoo1 #LavaCon
Making Suggestions
Printers
Requirements
Minimum requirements
Scanning
Faxing
Printing
Features
Copying
Wi-Fi
Recommended requirements
How to scan
How to faxing
How to print
Procedures
How to copy
see also
@Ditatoo1 #LavaCon
Making Suggestions
Printers
Requirements
Minimum requirements
Scanning
Faxing
Printing
Features
Copying
Wi-Fi
Recommended requirements
How to scan
How to faxing
How to print
Procedures
How to copy
see also
@Ditatoo1 #LavaCon
Making Suggestions
Printers
Requirements
Minimum requirements
Scanning
Faxing
Printing
Features
Copying
Wi-Fi
Recommended requirements
How to scan
How to faxing
How to print
Procedures
How to copy
see also
@Ditatoo1 #LavaCon
Ontology
Taxonomy
Semantic
Relationships
Rules
Inference
APILinkage
@Ditatoo1 #LavaCon
Ontology Formats
• OWL
• RDF/XML
• Semantic Web Rule Language (SWRL)
• CycL
@Ditatoo1 #LavaCon
How to Create?
• Ontology editors:
• Protégé
• Fluent Editor
• API:
• Jena API
• OWL API
• Automatically:
• Intuillion NLP
• PoolParty
@Ditatoo1 #LavaCon
Why Chatbot Gives Wrong Answers
• The issue is not covered by any content
• The content that covers the issue is too generic
• The metadata model does not match the elements of the user’s context
• No metadata is provided at all or wrong metadata is provided
• Metadata is not specific enough
• The piece of content includes information about multiple subjects
• The chatbot didn’t understand the user’s question at all or understood it
incorrectly
@Ditatoo1 #LavaCon
Exercise
Identify the problems with the content and offer solutions
@Ditatoo1 #LavaCon
Misunderstanding User’s Question
• Mapping to a wrong intent
• Mapping isn’t compatible (user has his own understanding of how the
product works)
• Solution:
• Calculation of the confidence score that indicates how confident
the chatbot is that the found content addresses the issue
• Feedback from the user about how relevant and helpful the
chatbot’s answer was
• Log of each conversation between the chatbot and the user
• Ability to hand over the issue to a human at any moment
@Ditatoo1 #LavaCon
Practical Steps: Taxonomy & Ontology
• Create a taxonomy:
• Who may need it?
• How may they use it?
• Analyze how the current content is linked:
• Do links represent semantic relationships?
• Is there content created by other departments?
• What the taxonomy doesn’t tell?
@Ditatoo1 #LavaCon
Practical Steps: Chatbot
• Do you really need it?
• Can be the same thing done with a wizard (another UI)?
• Do you really need a conversation?
• What additional value the chatbot will bring?
• What level of variety should the chatbot support?
• Do you want it to be proactive?
@Ditatoo1 #LavaCon
Summary
• Traditional intent and named entity recognition are expensive to scale.
• To make chatbots more scalable and less brittle, they need a formalized
semantic model of the domain (ontology).
• Ontology represents concepts and sematic relationships between them.
• Ontology is written in a machine-readable format.
• Ontology makes knowledge multi-dimensional and enables inference.
• Content needs to be as granular as user’s context.
• Content needs to be enriched with semantic metadata.
• The chatbot should provide a mechanism that lets you track what went.
wrong during the conversation and fix it.
@Ditatoo1 #LavaCon
Website: http://www.intuillion.com
Email: alex@intuillion.com
Contact Me
LinkedIn: DITAToo Community

To Make Your Chatbot Smart, You Need to Feed It Right: How to Write for Chatbots | Alex Masycheff