SlideShare a Scribd company logo
When privacy matters !
Chatbots in data-sensitive businesses
GraphAware, world’s #1 Neo4j consultancy
Creators of Hume - AI for Humans
graphaware.com
@graph_aware
Christophe Willemsen
CTO GraphAware
@ikwattro
● A word on data privacy
● Build your own : expectations vs reality
● Natural Language Processing
● Challenges with NLP
● Sentiment
● Q & A
Outline
A word on data privacy
● Where data is sent ?
● What is sensitive ?
● Are your users aware ?
Data Privacy
Build your own :
expectations
Business guy
Business guy I WANT A
CHATBOT
IT Department
IT Department
DataScience ARMY
Build your own :
expectations
● Creating a Chatbot with Deep Learning, Python, and TensorFlow
● How Chatbots Are Learning Emotions Using Deep Learning
● How I Used Deep Learning To Train A Chatbot To Talk Like Me
● Neuralconvo - Chatting with a Deep learning brain
● ...
Current conversation topics
● Creating a Chatbot with Deep Learning, Python, and TensorFlow
● How Chatbots Are Learning Emotions Using Deep Learning
● How I Used Deep Learning To Train A Chatbot To Talk Like Me
● Neuralconvo - Chatting with a Deep learning brain
● …
● Training your Machine Learning models on the blockchain
● Conversational Artificial Intelligence in the FinTech
Current conversation topics
Build your own :
reality
Conversation Flow
● It is the identification and categorization of what a user online
intended or wanted when they typed their query
Intent detection
Conversation Flow
Business guy
● It is the identification and categorization of what a user online
intended or wanted when they typed their
● Intent detection using semantically enriched word embeddings
● Zero-shot User Intent Detection via Capsule Neural Networks
● A Bi-model based RNN Semantic Frame Parsing Model for Intent
Detection and Slot Filling
Intent detection
Business guy
● Naive Bayes classifier
Intent detection
Intent detection
Build your own :
Challenges with NLP
● Bot : Hi, I am your health assistant, how can I help you ?
● User : I have a cough
Named Entity Recognition
● Bot : Hi, I am your health assistant, how can I help you ?
● User : I have a cough
Named Entity Recognition
● Bot : Hi, I am your health assistant, how can I help you ?
● User : I have a cough
Named Entity Recognition
SYMPTOM
Named Entity Recognition
Finding data
Named Entity Recognition
Finding data
Named Entity Recognition
Finding data
Named Entity Recognition
Finding data
hume.ga/ner
Build your own :
Challenges with NLP
Coreference Resolution
● Bot : Hi, I am your health assistant, how can I help you ?
● User : I have pain in the neck, it is really burning
Coreference Resolution
● Bot : Hi, I am your health assistant, how can I help you ?
● User : I have pain in the neck, it is really burning
Refers to
Coreference Resolution
Coreference Resolution
Build your own :
Challenges with NLP
Sentiment Analysis
● Sentiment analysis aims to determine the attitude of a speaker,
writer, or other subject with respect to some topic or the overall
contextual polarity or emotional reaction to a document,
interaction, or event
Sentiment Analysis
Sentiment Analysis
Sentiment Analysis
● If chatbots are not your primary mean of communication, it
means you failed at other points ( the user could not find the
information online )
● A typical negative, neutral, positive polarity does not reflect the
reality
Sentiment Analysis
angry
Very angry
I’m gonna find your family
Build your own :
Challenges with NLP
Expectations vs reality
● Bot : I am your financial assistant, how can I help you ?
● User : Hi, I could not login into the online banking system
Expectations vs reality
● Bot : I am your financial assistant, how can I help you ?
● User : Hi, I could not login into the online banking system
● The app doesn’t work, dunno man, wtf ?
Expectations vs reality
● Bot : I am your health assistant, how can I help you ?
● User : Hi, I have a cough
Expectations vs reality
● Bot : I am your health assistant, how can I help you ?
● User : Hi, I have a cough
● ‫ﺳﻌﺎل‬ ‫ﻋﻧدي‬ ، ً‫ﺎ‬‫ﻣرﺣﺑ‬
Expectations vs reality
● Bot : I am your health assistant, how can I help you ?
● User : Hi, I have a cough
● ‫ﺳﻌﺎل‬ ‫ﻋﻧدي‬ ، ً‫ﺎ‬‫ﻣرﺣﺑ‬
● Most NLP Processing techniques for English do not work for
Arabic
● Arabic has 40 dialects
● POS tagging is dependant on the domain
● etc...
Build your own :
So what’s the point now ?
Data-privacy is a trade-off
● When you make the choice of data-privacy, you have trade-offs
○ You do not sit on the shoulders on giants anymore
○ The cost of research will exponentially surpass the usage cost
of a third-party solution
○ You have the sole responsibility of the satisfaction of the
customers
It has to work 100% of the times
“I don’t understand your
question”
is not an answer
It’s an insult !
Integrate all the things
● Intent Detection
● Natural Language Processing
● Custom Named Entity model training
● Co-reference resolution training
● English, Arabic, German support
● Graph-based context builder
hume.ga
graphaware.com
Questions ?

More Related Content

Similar to When privacy matters! Chatbots in data-sensitive businesses

How Do You Know if Your Project Is Any Good?
How Do You Know if Your Project Is Any Good?How Do You Know if Your Project Is Any Good?
How Do You Know if Your Project Is Any Good?
All Things Open
 
Improving Analytics Success through Communication
Improving Analytics Success through CommunicationImproving Analytics Success through Communication
Improving Analytics Success through Communication
Anna Lewis
 
Libraries & Social Media
Libraries & Social MediaLibraries & Social Media
Libraries & Social Media
Liz McCarthy
 
User Experience Research: Deriving Insights for Customer Development
User Experience Research: Deriving Insights for Customer DevelopmentUser Experience Research: Deriving Insights for Customer Development
User Experience Research: Deriving Insights for Customer Development
Noreen Whysel
 
Buyer personas & Customer journey
Buyer personas & Customer journeyBuyer personas & Customer journey
Buyer personas & Customer journey
Filippo Scorza
 
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Jon Temple
 
5 Secrets of Tech Marketing
5 Secrets of Tech Marketing5 Secrets of Tech Marketing
5 Secrets of Tech Marketing
Oomph, Inc.
 
Take the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstreamTake the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstream
Rico Lin
 
Marketing Edition: How we leverage UserTesting
Marketing Edition: How we leverage UserTesting Marketing Edition: How we leverage UserTesting
Marketing Edition: How we leverage UserTesting
UserTesting
 
Dealing with contributor overload - FOSS Backstage
Dealing with contributor overload -  FOSS BackstageDealing with contributor overload -  FOSS Backstage
Dealing with contributor overload - FOSS Backstage
Holden Karau
 
Building A Lead Generating Chatbot
Building A Lead Generating ChatbotBuilding A Lead Generating Chatbot
Building A Lead Generating Chatbot
Whitehat Inbound Marketing Agency
 
Content Creation live Workshop
Content Creation live WorkshopContent Creation live Workshop
Content Creation live Workshop
The Fiery Well, LLC
 
Motivation[1]
Motivation[1]Motivation[1]
Motivation[1]
Michael P. Shikemeni
 
From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business
From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business
From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business
Matthew Albert
 
Multimodal opinion mining from social media
Multimodal opinion mining from social mediaMultimodal opinion mining from social media
Multimodal opinion mining from social media
Diana Maynard
 
Take the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstreamTake the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstream
Rico Lin
 
UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...
UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...
UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...
UX STRAT
 
Content 101 - Training in content for budding entrepreneurs
Content 101 - Training in content for budding entrepreneursContent 101 - Training in content for budding entrepreneurs
Content 101 - Training in content for budding entrepreneurs
Brutal Pixie
 
StartupCamp Bratislava#34 - Running Lean Up To MVP
StartupCamp Bratislava#34 - Running Lean Up To MVPStartupCamp Bratislava#34 - Running Lean Up To MVP
StartupCamp Bratislava#34 - Running Lean Up To MVP
StartupCamp
 
Marketing Addiction Treatment, Prevention and Recovery Programs
Marketing Addiction Treatment, Prevention and Recovery ProgramsMarketing Addiction Treatment, Prevention and Recovery Programs
Marketing Addiction Treatment, Prevention and Recovery Programs
Jennifer Iacovelli
 

Similar to When privacy matters! Chatbots in data-sensitive businesses (20)

How Do You Know if Your Project Is Any Good?
How Do You Know if Your Project Is Any Good?How Do You Know if Your Project Is Any Good?
How Do You Know if Your Project Is Any Good?
 
Improving Analytics Success through Communication
Improving Analytics Success through CommunicationImproving Analytics Success through Communication
Improving Analytics Success through Communication
 
Libraries & Social Media
Libraries & Social MediaLibraries & Social Media
Libraries & Social Media
 
User Experience Research: Deriving Insights for Customer Development
User Experience Research: Deriving Insights for Customer DevelopmentUser Experience Research: Deriving Insights for Customer Development
User Experience Research: Deriving Insights for Customer Development
 
Buyer personas & Customer journey
Buyer personas & Customer journeyBuyer personas & Customer journey
Buyer personas & Customer journey
 
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...Workshop: Chatbot in a box - Introduction to conversation design and conducti...
Workshop: Chatbot in a box - Introduction to conversation design and conducti...
 
5 Secrets of Tech Marketing
5 Secrets of Tech Marketing5 Secrets of Tech Marketing
5 Secrets of Tech Marketing
 
Take the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstreamTake the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstream
 
Marketing Edition: How we leverage UserTesting
Marketing Edition: How we leverage UserTesting Marketing Edition: How we leverage UserTesting
Marketing Edition: How we leverage UserTesting
 
Dealing with contributor overload - FOSS Backstage
Dealing with contributor overload -  FOSS BackstageDealing with contributor overload -  FOSS Backstage
Dealing with contributor overload - FOSS Backstage
 
Building A Lead Generating Chatbot
Building A Lead Generating ChatbotBuilding A Lead Generating Chatbot
Building A Lead Generating Chatbot
 
Content Creation live Workshop
Content Creation live WorkshopContent Creation live Workshop
Content Creation live Workshop
 
Motivation[1]
Motivation[1]Motivation[1]
Motivation[1]
 
From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business
From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business
From Zero to Live: How To Launch, Grow and Monetize A Podcast For Your Business
 
Multimodal opinion mining from social media
Multimodal opinion mining from social mediaMultimodal opinion mining from social media
Multimodal opinion mining from social media
 
Take the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstreamTake the advantage and connect upstream to downstream
Take the advantage and connect upstream to downstream
 
UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...
UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...
UX STRAT Europe 2017: Gregory Ek: “Experience Strategy for Digital Conversati...
 
Content 101 - Training in content for budding entrepreneurs
Content 101 - Training in content for budding entrepreneursContent 101 - Training in content for budding entrepreneurs
Content 101 - Training in content for budding entrepreneurs
 
StartupCamp Bratislava#34 - Running Lean Up To MVP
StartupCamp Bratislava#34 - Running Lean Up To MVPStartupCamp Bratislava#34 - Running Lean Up To MVP
StartupCamp Bratislava#34 - Running Lean Up To MVP
 
Marketing Addiction Treatment, Prevention and Recovery Programs
Marketing Addiction Treatment, Prevention and Recovery ProgramsMarketing Addiction Treatment, Prevention and Recovery Programs
Marketing Addiction Treatment, Prevention and Recovery Programs
 

More from GraphAware

Unparalleled Graph Database Scalability Delivered by Neo4j 4.0
Unparalleled Graph Database Scalability Delivered by Neo4j 4.0Unparalleled Graph Database Scalability Delivered by Neo4j 4.0
Unparalleled Graph Database Scalability Delivered by Neo4j 4.0
GraphAware
 
Challenges in knowledge graph visualization
Challenges in knowledge graph visualizationChallenges in knowledge graph visualization
Challenges in knowledge graph visualization
GraphAware
 
Social media monitoring with ML-powered Knowledge Graph
Social media monitoring with ML-powered Knowledge GraphSocial media monitoring with ML-powered Knowledge Graph
Social media monitoring with ML-powered Knowledge Graph
GraphAware
 
To be or not to be.
To be or not to be. To be or not to be.
To be or not to be.
GraphAware
 
It Depends (and why it's the most frequent answer to modelling questions)
It Depends (and why it's the most frequent answer to modelling questions)It Depends (and why it's the most frequent answer to modelling questions)
It Depends (and why it's the most frequent answer to modelling questions)
GraphAware
 
How Boston Scientific Improves Manufacturing Quality Using Graph Analytics
How Boston Scientific Improves Manufacturing Quality Using Graph AnalyticsHow Boston Scientific Improves Manufacturing Quality Using Graph Analytics
How Boston Scientific Improves Manufacturing Quality Using Graph Analytics
GraphAware
 
Graph-Powered Machine Learning
Graph-Powered Machine LearningGraph-Powered Machine Learning
Graph-Powered Machine Learning
GraphAware
 
Signals from outer space
Signals from outer spaceSignals from outer space
Signals from outer space
GraphAware
 
Neo4j-Databridge: Enterprise-scale ETL for Neo4j
Neo4j-Databridge: Enterprise-scale ETL for Neo4jNeo4j-Databridge: Enterprise-scale ETL for Neo4j
Neo4j-Databridge: Enterprise-scale ETL for Neo4j
GraphAware
 
Graph-Powered Machine Learning
Graph-Powered Machine Learning Graph-Powered Machine Learning
Graph-Powered Machine Learning
GraphAware
 
(Big) Data Science
 (Big) Data Science (Big) Data Science
(Big) Data Science
GraphAware
 
Modelling Data in Neo4j (plus a few tips)
Modelling Data in Neo4j (plus a few tips)Modelling Data in Neo4j (plus a few tips)
Modelling Data in Neo4j (plus a few tips)
GraphAware
 
Intro to Neo4j (CZ)
Intro to Neo4j (CZ)Intro to Neo4j (CZ)
Intro to Neo4j (CZ)
GraphAware
 
Modelling Data as Graphs (Neo4j)
Modelling Data as Graphs (Neo4j)Modelling Data as Graphs (Neo4j)
Modelling Data as Graphs (Neo4j)
GraphAware
 
GraphAware Framework Intro
GraphAware Framework IntroGraphAware Framework Intro
GraphAware Framework Intro
GraphAware
 
Advanced Neo4j Use Cases with the GraphAware Framework
Advanced Neo4j Use Cases with the GraphAware FrameworkAdvanced Neo4j Use Cases with the GraphAware Framework
Advanced Neo4j Use Cases with the GraphAware Framework
GraphAware
 
Recommendations with Neo4j (FOSDEM 2015)
Recommendations with Neo4j (FOSDEM 2015)Recommendations with Neo4j (FOSDEM 2015)
Recommendations with Neo4j (FOSDEM 2015)
GraphAware
 
Machine Learning Powered by Graphs - Alessandro Negro
Machine Learning Powered by Graphs - Alessandro NegroMachine Learning Powered by Graphs - Alessandro Negro
Machine Learning Powered by Graphs - Alessandro Negro
GraphAware
 
Knowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe Willemsen
Knowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe WillemsenKnowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe Willemsen
Knowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe Willemsen
GraphAware
 
The power of polyglot searching
The power of polyglot searchingThe power of polyglot searching
The power of polyglot searching
GraphAware
 

More from GraphAware (20)

Unparalleled Graph Database Scalability Delivered by Neo4j 4.0
Unparalleled Graph Database Scalability Delivered by Neo4j 4.0Unparalleled Graph Database Scalability Delivered by Neo4j 4.0
Unparalleled Graph Database Scalability Delivered by Neo4j 4.0
 
Challenges in knowledge graph visualization
Challenges in knowledge graph visualizationChallenges in knowledge graph visualization
Challenges in knowledge graph visualization
 
Social media monitoring with ML-powered Knowledge Graph
Social media monitoring with ML-powered Knowledge GraphSocial media monitoring with ML-powered Knowledge Graph
Social media monitoring with ML-powered Knowledge Graph
 
To be or not to be.
To be or not to be. To be or not to be.
To be or not to be.
 
It Depends (and why it's the most frequent answer to modelling questions)
It Depends (and why it's the most frequent answer to modelling questions)It Depends (and why it's the most frequent answer to modelling questions)
It Depends (and why it's the most frequent answer to modelling questions)
 
How Boston Scientific Improves Manufacturing Quality Using Graph Analytics
How Boston Scientific Improves Manufacturing Quality Using Graph AnalyticsHow Boston Scientific Improves Manufacturing Quality Using Graph Analytics
How Boston Scientific Improves Manufacturing Quality Using Graph Analytics
 
Graph-Powered Machine Learning
Graph-Powered Machine LearningGraph-Powered Machine Learning
Graph-Powered Machine Learning
 
Signals from outer space
Signals from outer spaceSignals from outer space
Signals from outer space
 
Neo4j-Databridge: Enterprise-scale ETL for Neo4j
Neo4j-Databridge: Enterprise-scale ETL for Neo4jNeo4j-Databridge: Enterprise-scale ETL for Neo4j
Neo4j-Databridge: Enterprise-scale ETL for Neo4j
 
Graph-Powered Machine Learning
Graph-Powered Machine Learning Graph-Powered Machine Learning
Graph-Powered Machine Learning
 
(Big) Data Science
 (Big) Data Science (Big) Data Science
(Big) Data Science
 
Modelling Data in Neo4j (plus a few tips)
Modelling Data in Neo4j (plus a few tips)Modelling Data in Neo4j (plus a few tips)
Modelling Data in Neo4j (plus a few tips)
 
Intro to Neo4j (CZ)
Intro to Neo4j (CZ)Intro to Neo4j (CZ)
Intro to Neo4j (CZ)
 
Modelling Data as Graphs (Neo4j)
Modelling Data as Graphs (Neo4j)Modelling Data as Graphs (Neo4j)
Modelling Data as Graphs (Neo4j)
 
GraphAware Framework Intro
GraphAware Framework IntroGraphAware Framework Intro
GraphAware Framework Intro
 
Advanced Neo4j Use Cases with the GraphAware Framework
Advanced Neo4j Use Cases with the GraphAware FrameworkAdvanced Neo4j Use Cases with the GraphAware Framework
Advanced Neo4j Use Cases with the GraphAware Framework
 
Recommendations with Neo4j (FOSDEM 2015)
Recommendations with Neo4j (FOSDEM 2015)Recommendations with Neo4j (FOSDEM 2015)
Recommendations with Neo4j (FOSDEM 2015)
 
Machine Learning Powered by Graphs - Alessandro Negro
Machine Learning Powered by Graphs - Alessandro NegroMachine Learning Powered by Graphs - Alessandro Negro
Machine Learning Powered by Graphs - Alessandro Negro
 
Knowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe Willemsen
Knowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe WillemsenKnowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe Willemsen
Knowledge Graphs and Chatbots with Neo4j and IBM Watson - Christophe Willemsen
 
The power of polyglot searching
The power of polyglot searchingThe power of polyglot searching
The power of polyglot searching
 

Recently uploaded

Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving
 
Apps Break Data
Apps Break DataApps Break Data
Apps Break Data
Ivo Velitchkov
 
What is an RPA CoE? Session 2 – CoE Roles
What is an RPA CoE?  Session 2 – CoE RolesWhat is an RPA CoE?  Session 2 – CoE Roles
What is an RPA CoE? Session 2 – CoE Roles
DianaGray10
 
Guidelines for Effective Data Visualization
Guidelines for Effective Data VisualizationGuidelines for Effective Data Visualization
Guidelines for Effective Data Visualization
UmmeSalmaM1
 
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users",  Kevin Goedecke"Scaling RAG Applications to serve millions of users",  Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
Fwdays
 
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
manji sharman06
 
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
Getting the Most Out of ScyllaDB Monitoring: ShareChat's TipsGetting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
ScyllaDB
 
Cyber Recovery Wargame
Cyber Recovery WargameCyber Recovery Wargame
Cyber Recovery Wargame
Databarracks
 
Christine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptxChristine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptx
christinelarrosa
 
Session 1 - Intro to Robotic Process Automation.pdf
Session 1 - Intro to Robotic Process Automation.pdfSession 1 - Intro to Robotic Process Automation.pdf
Session 1 - Intro to Robotic Process Automation.pdf
UiPathCommunity
 
Automation Student Developers Session 3: Introduction to UI Automation
Automation Student Developers Session 3: Introduction to UI AutomationAutomation Student Developers Session 3: Introduction to UI Automation
Automation Student Developers Session 3: Introduction to UI Automation
UiPathCommunity
 
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - MydbopsMySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
Mydbops
 
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham HillinQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
LizaNolte
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
DianaGray10
 
"NATO Hackathon Winner: AI-Powered Drug Search", Taras Kloba
"NATO Hackathon Winner: AI-Powered Drug Search",  Taras Kloba"NATO Hackathon Winner: AI-Powered Drug Search",  Taras Kloba
"NATO Hackathon Winner: AI-Powered Drug Search", Taras Kloba
Fwdays
 
ScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking ReplicationScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking Replication
ScyllaDB
 
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
Fwdays
 
TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...
TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...
TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...
TrustArc
 
"What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w..."What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w...
Fwdays
 
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdfLee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
leebarnesutopia
 

Recently uploaded (20)

Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving | Nameplate Manufacturing Process - 2024
Northern Engraving | Nameplate Manufacturing Process - 2024
 
Apps Break Data
Apps Break DataApps Break Data
Apps Break Data
 
What is an RPA CoE? Session 2 – CoE Roles
What is an RPA CoE?  Session 2 – CoE RolesWhat is an RPA CoE?  Session 2 – CoE Roles
What is an RPA CoE? Session 2 – CoE Roles
 
Guidelines for Effective Data Visualization
Guidelines for Effective Data VisualizationGuidelines for Effective Data Visualization
Guidelines for Effective Data Visualization
 
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users",  Kevin Goedecke"Scaling RAG Applications to serve millions of users",  Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
 
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
Call Girls Chandigarh🔥7023059433🔥Agency Profile Escorts in Chandigarh Availab...
 
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
Getting the Most Out of ScyllaDB Monitoring: ShareChat's TipsGetting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
 
Cyber Recovery Wargame
Cyber Recovery WargameCyber Recovery Wargame
Cyber Recovery Wargame
 
Christine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptxChristine's Product Research Presentation.pptx
Christine's Product Research Presentation.pptx
 
Session 1 - Intro to Robotic Process Automation.pdf
Session 1 - Intro to Robotic Process Automation.pdfSession 1 - Intro to Robotic Process Automation.pdf
Session 1 - Intro to Robotic Process Automation.pdf
 
Automation Student Developers Session 3: Introduction to UI Automation
Automation Student Developers Session 3: Introduction to UI AutomationAutomation Student Developers Session 3: Introduction to UI Automation
Automation Student Developers Session 3: Introduction to UI Automation
 
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - MydbopsMySQL InnoDB Storage Engine: Deep Dive - Mydbops
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
 
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham HillinQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
inQuba Webinar Mastering Customer Journey Management with Dr Graham Hill
 
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsConnector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
 
"NATO Hackathon Winner: AI-Powered Drug Search", Taras Kloba
"NATO Hackathon Winner: AI-Powered Drug Search",  Taras Kloba"NATO Hackathon Winner: AI-Powered Drug Search",  Taras Kloba
"NATO Hackathon Winner: AI-Powered Drug Search", Taras Kloba
 
ScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking ReplicationScyllaDB Tablets: Rethinking Replication
ScyllaDB Tablets: Rethinking Replication
 
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk"Frontline Battles with DDoS: Best practices and Lessons Learned",  Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
 
TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...
TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...
TrustArc Webinar - Your Guide for Smooth Cross-Border Data Transfers and Glob...
 
"What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w..."What does it really mean for your system to be available, or how to define w...
"What does it really mean for your system to be available, or how to define w...
 
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdfLee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
 

When privacy matters! Chatbots in data-sensitive businesses

  • 1. When privacy matters ! Chatbots in data-sensitive businesses GraphAware, world’s #1 Neo4j consultancy Creators of Hume - AI for Humans graphaware.com @graph_aware Christophe Willemsen CTO GraphAware @ikwattro
  • 2. ● A word on data privacy ● Build your own : expectations vs reality ● Natural Language Processing ● Challenges with NLP ● Sentiment ● Q & A Outline
  • 3. A word on data privacy
  • 4. ● Where data is sent ? ● What is sensitive ? ● Are your users aware ? Data Privacy
  • 5. Build your own : expectations
  • 7. Business guy I WANT A CHATBOT
  • 11. Build your own : expectations
  • 12. ● Creating a Chatbot with Deep Learning, Python, and TensorFlow ● How Chatbots Are Learning Emotions Using Deep Learning ● How I Used Deep Learning To Train A Chatbot To Talk Like Me ● Neuralconvo - Chatting with a Deep learning brain ● ... Current conversation topics
  • 13. ● Creating a Chatbot with Deep Learning, Python, and TensorFlow ● How Chatbots Are Learning Emotions Using Deep Learning ● How I Used Deep Learning To Train A Chatbot To Talk Like Me ● Neuralconvo - Chatting with a Deep learning brain ● … ● Training your Machine Learning models on the blockchain ● Conversational Artificial Intelligence in the FinTech Current conversation topics
  • 14. Build your own : reality
  • 16. ● It is the identification and categorization of what a user online intended or wanted when they typed their query Intent detection
  • 19. ● It is the identification and categorization of what a user online intended or wanted when they typed their ● Intent detection using semantically enriched word embeddings ● Zero-shot User Intent Detection via Capsule Neural Networks ● A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling Intent detection
  • 21.
  • 22. ● Naive Bayes classifier Intent detection
  • 24. Build your own : Challenges with NLP
  • 25. ● Bot : Hi, I am your health assistant, how can I help you ? ● User : I have a cough Named Entity Recognition
  • 26. ● Bot : Hi, I am your health assistant, how can I help you ? ● User : I have a cough Named Entity Recognition
  • 27. ● Bot : Hi, I am your health assistant, how can I help you ? ● User : I have a cough Named Entity Recognition SYMPTOM
  • 33. Build your own : Challenges with NLP
  • 34. Coreference Resolution ● Bot : Hi, I am your health assistant, how can I help you ? ● User : I have pain in the neck, it is really burning
  • 35. Coreference Resolution ● Bot : Hi, I am your health assistant, how can I help you ? ● User : I have pain in the neck, it is really burning Refers to
  • 38. Build your own : Challenges with NLP
  • 39. Sentiment Analysis ● Sentiment analysis aims to determine the attitude of a speaker, writer, or other subject with respect to some topic or the overall contextual polarity or emotional reaction to a document, interaction, or event
  • 42. Sentiment Analysis ● If chatbots are not your primary mean of communication, it means you failed at other points ( the user could not find the information online ) ● A typical negative, neutral, positive polarity does not reflect the reality
  • 44. Build your own : Challenges with NLP
  • 45. Expectations vs reality ● Bot : I am your financial assistant, how can I help you ? ● User : Hi, I could not login into the online banking system
  • 46. Expectations vs reality ● Bot : I am your financial assistant, how can I help you ? ● User : Hi, I could not login into the online banking system ● The app doesn’t work, dunno man, wtf ?
  • 47. Expectations vs reality ● Bot : I am your health assistant, how can I help you ? ● User : Hi, I have a cough
  • 48. Expectations vs reality ● Bot : I am your health assistant, how can I help you ? ● User : Hi, I have a cough ● ‫ﺳﻌﺎل‬ ‫ﻋﻧدي‬ ، ً‫ﺎ‬‫ﻣرﺣﺑ‬
  • 49. Expectations vs reality ● Bot : I am your health assistant, how can I help you ? ● User : Hi, I have a cough ● ‫ﺳﻌﺎل‬ ‫ﻋﻧدي‬ ، ً‫ﺎ‬‫ﻣرﺣﺑ‬ ● Most NLP Processing techniques for English do not work for Arabic ● Arabic has 40 dialects ● POS tagging is dependant on the domain ● etc...
  • 50. Build your own : So what’s the point now ?
  • 51. Data-privacy is a trade-off ● When you make the choice of data-privacy, you have trade-offs ○ You do not sit on the shoulders on giants anymore ○ The cost of research will exponentially surpass the usage cost of a third-party solution ○ You have the sole responsibility of the satisfaction of the customers
  • 52. It has to work 100% of the times
  • 53. “I don’t understand your question” is not an answer
  • 55. Integrate all the things ● Intent Detection ● Natural Language Processing ● Custom Named Entity model training ● Co-reference resolution training ● English, Arabic, German support ● Graph-based context builder
  • 57.