e g a l l i v a s e k a t It t o b a e s i a r to
Desiree García @thedezzie
Slide 2
Slide 3
Conversational systems and emerging AI
Slide 4
"Just add water"
Slide 5
Slide 6
"One size fits all"
Slide 7
Slide 8
Slide 9
Engineers couldn't do it alone.
Slide 10
Why do people want conversational systems?
Slide 11
“Don’t play what’s there, play what’s not there.”
Miles Davis
Slide 12
Machines still have a hard time with language
http://bit.ly/ai-language-problems
Slide 13
Simple conversational systems that are great
Slide 14
Slide 15
Complex conversational systems that are great
Slide 16
Slide 17
Slide 18
Slide 19
Time + Money
Slide 20
Is it convincing?
Slide 21
Is it convincing effective?
Slide 22
Content first
Slide 23
Content last
Slide 24
Intents
Entities
Dialog builder
#greeting Conversation starts
Condition
#greeting Watson responses (0)
No responses added
Edit .
Order pizza flow and some …
Order pizza flow and some …
Condition
Condition
No conditions set
No conditions set
Watson responses
20
We got ya down for a $topping pizza.
Anything else
Watson responses
20
We got ya down for a $topping pizza.
Introduction
Slide 25
@location
.
@restaurant
@cuisine
Slide 26
"In just minutes a day"
Slide 27
Getting people to train a conversational system is as easy as getting people to start exercising .
Slide 28
.
http://www.r2d3.us/
Slide 29
Initial training ingestion employee manual
Initial training improvement apprenticeship
ongoing training refinement mastery
Slide 30
Content matters, because training matters
Slide 31
Deploy your conversational system app Assess its performance using human judgment Optimize its operating thresholds Retrain machine learning model with golden examples from humans 5. Lather, rinse, repeat
Slide 32
Deploy your conversational system app Assess its performance using human judgment Optimize its operating thresholds Retrain machine learning model with golden examples from humans 5. Lather, rinse, repeat
Slide 33
"Shut it down, shut it down!"
Slide 34
In AI, everyone is learning as they go along
Slide 35
They built teams.
Slide 36
developer
domain expert sme content strategist ux designer
Slide 37
developer
domain expert
Slide 38
Intents
Entities
Dialog builder
#greeting Conversation starts
Condition
#greeting Watson responses (0)
No responses added
Edit .
Order pizza flow and some …
Order pizza flow and some …
Condition
Condition
No conditions set
No conditions set
Watson responses
20
We got ya down for a $topping pizza.
Anything else
Watson responses
20
We got ya down for a $topping pizza.
Introduction
Slide 39
@location
. .
#recommend
@restaurant
@cuisine
Slide 40
Empowering the creators
Slide 41
developer
business
domain expert
data scientist
Slide 42
domain expert
Slide 43
"Ther
e's w ater i n my room !"
e k i l u o y d l "Wou e m o s u o y bring
us to ice?"
Slide 44
They're closest to the content
Slide 45
moar content
engineer
data scientist
domain expert business
Slide 46
How's your relationship to content?
Slide 47
moar content
engineer
data scientist
domain expert business
Slide 48
"It's just content"
Slide 49
When you appropriate a domain or discipline that you don't know, you are unaware of your biases
Slide 50
Slide 51
"It's just content"
Slide 52
...what if you don't need AI?
Slide 53
Slide 54
Yay!
Slide 55
Inspiration for this talk
Slide 56
Slide 57
Would you put a baby in charge of customer support?
Slide 58
How about letting a toddler recommend medical treatment?
Slide 59
Or getting financial advice from a teenager?
Slide 60
It takes a village to raise a chatbot
Slide 61
Thank you! These slides live here: bit.ly/raising-chatbots An visual introduction to machine learning: r2d3.us A review of chatbot platforms bit.ly/chatbot-platforms An excellent guide to conversational design Conversational Design by Erika Hall (A Book Apart) Sparkle and Spin - A Book About Words, by Ann Rand and Paul Rand Twitter: @thedezzie Email: dezzie@automattic.com