SlideShare a Scribd company logo
CHATBOTS AND AI
ARE ALL CHATBOTS
CREATED EQUAL?
NOT WHAT CONVERSATION IS ABOUT
SCRIPTED CHATBOTS
A BIT DECEPTIVE SO FAR?
AI BOTS
Vertical vs Horizontal bots
IT’S NOT ABOUT DEEP LEARNING ONLY
AI ML
NLP
DL
Expert systems
Grammars
ARTIFICIAL INTELLIGENCE ACHIEVEMENTS
RL
ANATOMY OF A BOT
Natural
Language
Under-
standing
“I haven’t
received my
shoes I ordered
last week”
Intent: Delivery
problem
Product: Shoes
Date: Last_week
INPUT
Dialog
system
Business
logic
TRANSFORMATION INTO
STRUCTURED DATA
Action: Indicate
delivery status
Delivery date:
Tomorrow
Reason for delay:
Shortage
Natural
language
generation
Parse the input of the user to
extract the meaning behind
it, ideally observing context
FETCHING RESULTS FROM
BACKEND SERVICES
Provide information, insights
and functionality from the
input
FORMULATE
ANSWER
Organize
information in a
coherent,
readable format
“We are sorry.
There was a
shortage on
these shoes.
You will
receive them
tomorrow”
OUTPUT
HOW AI CAN HELP WITH CHATBOTS THOUGH?
MACHINE LEARNING FOR NLP
VR AND
TEXT TO SPEECH
POS TAGGING
SENTIMENT
ANALYSIS
NATURAL
LANGUAGE
GENERATION
MACHINE
TRANSLATION
DEPENDENCY
PARSING
ALREADY MANY ACHIEVEMENTS
TEXT NEEDS CONTEXT
Cat
Kitten
Mat?
Discrete atomic
symbols
THE PROBLEM WITH TEXT
EMBEDDINGS
How words and sentences can be turned
into numbers that machines can work with
BACKGROUND
Recent but successful technique
Unsupervisedly learned word embeddings have
been exceptionally successful in many NLP tasks.
Maybe the primary reason for NLP's breakout.
Encoding general semantic relationships
Beneficial to many downstream tasks
Distributional hypothesis
Words that are used and occur in the same
contexts tend to purport similar meanings.
VECTOR SPACE MODELS
0 1 0 0 1 0 0 0 0 0 0 0 2 0 1 0Cat
VECTOR SPACE MODELS
0 1 0 0 1 0 0 0 0 0 2 0 1 0Cat
Doc2 Doc5 Doc11 Doc13
Could be word counts in documents
VECTOR SPACE MODELS
0 1 0 0 1 0 0 0 0 0 1 0 1 0
cat cute drinks milk
Bag of words, frequency count
Bi-grams …. N-grams
my cat is so cute when he drinks milk
EMBEDDINGS
Vectors discussed so far
are very high
dimensional
Techniques used to
learn
lower-dimensional
vectors are called
embeddings
LEARNING DENSE EMBEDDINGS
Matrix factorization
Glove, 2014
Shallow Neural
Networks
Word2Vec, 2013
MAIN ADVANTAGES
● One of the few currently successful applications of
unsupervised learning.
● Can be derived from large sets of unannotated corpora
● Pre-trained embeddings can then be used in
downstream tasks that use small amounts of labeled
data.
WHAT CAN BE ACHIEVED?
NEIGHBOURING SPACES
SIMILARITY
SIMILARITIES
WORD ANALOGY
ANALOGIES
INTENT CLASSIFICATION
Word embeddings are especially helpful when there is little
training data
I will travel to New York tomorrow
I will leave for New York tomorrow
I will take a flight to New York tomorrow
{intent: travel}
ENTITY RECOGNITION
Do you know a good vietnamese restaurant?
{restaurant_types: [italian french, japanese]}
{restaurant_type: vietnamese}
SOME REFERENCES
Mikolov, T., Corrado, G., Chen, K., & Dean, J. (2013). Efficient Estimation of
Word Representations in Vector Space. Proceedings of the International
Conference on Learning Representations (ICLR 2013), 1–12.
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Distributed
Representations of Words and Phrases and their Compositionality. NIPS, 1–9.
Bootstrapping Dialog Systems with Word Embeddings
https://www.cs.cmu.edu/~apparikh/nips2014ml-nlp/camera-ready/forgues_e
tal_mlnlp2014.pdf
https://www.npmjs.com/package/word2vec
https://radimrehurek.com/gensim/
TELL US WHICH BOT YOU NEED,
WE MOST PROBABLY KNOW HOW TO DO IT
Web
http://botfuel.io
E-mail
sales@botfuel.io
Fueling the next generation of bots

More Related Content

What's hot

Chatbots 101
Chatbots 101Chatbots 101
Chatbots 101
Venu Vasudevan
 
Chatbots
ChatbotsChatbots
Chatbots - The Next Generation Technology
Chatbots - The Next Generation TechnologyChatbots - The Next Generation Technology
Chatbots - The Next Generation Technology
aakash malhotra
 
Digital Transformation
Digital Transformation Digital Transformation
Digital Transformation
Heru WIjayanto
 
Smart contracts
Smart contractsSmart contracts
Smart contracts
Philippe Camacho, Ph.D.
 
How Chatbots Can Transform Your Business
How Chatbots Can Transform Your BusinessHow Chatbots Can Transform Your Business
How Chatbots Can Transform Your Business
Techedge Group
 
What is a chatbot?
What is a chatbot?What is a chatbot?
What is a chatbot?
Kamini Bharti
 
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational InterfacesThe Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
TWG
 
Web3 Fundamentals
Web3 FundamentalsWeb3 Fundamentals
Web3 Fundamentals
101 Blockchains
 
Chat Bots Presentation 8.9.16
Chat Bots Presentation 8.9.16Chat Bots Presentation 8.9.16
Chat Bots Presentation 8.9.16Samuel Adams, MBA
 
8 most important benefits of chatbots
8 most important benefits of chatbots8 most important benefits of chatbots
8 most important benefits of chatbots
MindTitan
 
Chat bots and AI
Chat bots and AIChat bots and AI
Chat bots and AI
Geff Thomas
 
Chatbot ppt
Chatbot pptChatbot ppt
Chatbot ppt
Manish Mishra
 
Artificial intelligence in industry
Artificial intelligence in industryArtificial intelligence in industry
Artificial intelligence in industry
Dipanjan Mitra
 
Chatbots - The Business Opportunity
Chatbots - The Business OpportunityChatbots - The Business Opportunity
Chatbots - The Business Opportunity
Alexandros Ivos
 
How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps
How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps
How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps
Bernard Marr
 
Digital Insurance Transformation
Digital Insurance TransformationDigital Insurance Transformation
Digital Insurance Transformation
TransInsure
 
Banking Chatbot
Banking ChatbotBanking Chatbot
Banking Chatbot
Waleed Khan
 
What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...
What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...
What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...
Maruti Techlabs
 

What's hot (20)

Chatbots 101
Chatbots 101Chatbots 101
Chatbots 101
 
Chatbots
ChatbotsChatbots
Chatbots
 
Chatbots - The Next Generation Technology
Chatbots - The Next Generation TechnologyChatbots - The Next Generation Technology
Chatbots - The Next Generation Technology
 
Digital Transformation
Digital Transformation Digital Transformation
Digital Transformation
 
Smart contracts
Smart contractsSmart contracts
Smart contracts
 
How Chatbots Can Transform Your Business
How Chatbots Can Transform Your BusinessHow Chatbots Can Transform Your Business
How Chatbots Can Transform Your Business
 
What is a chatbot?
What is a chatbot?What is a chatbot?
What is a chatbot?
 
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational InterfacesThe Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
The Chatbots Are Coming: A Guide to Chatbots, AI and Conversational Interfaces
 
Web3 Fundamentals
Web3 FundamentalsWeb3 Fundamentals
Web3 Fundamentals
 
Chat Bots Presentation 8.9.16
Chat Bots Presentation 8.9.16Chat Bots Presentation 8.9.16
Chat Bots Presentation 8.9.16
 
8 most important benefits of chatbots
8 most important benefits of chatbots8 most important benefits of chatbots
8 most important benefits of chatbots
 
Chat bots and AI
Chat bots and AIChat bots and AI
Chat bots and AI
 
Blockchain
BlockchainBlockchain
Blockchain
 
Chatbot ppt
Chatbot pptChatbot ppt
Chatbot ppt
 
Artificial intelligence in industry
Artificial intelligence in industryArtificial intelligence in industry
Artificial intelligence in industry
 
Chatbots - The Business Opportunity
Chatbots - The Business OpportunityChatbots - The Business Opportunity
Chatbots - The Business Opportunity
 
How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps
How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps
How To Identify The Best AI Opportunities For Your Business – In 2 Simple Steps
 
Digital Insurance Transformation
Digital Insurance TransformationDigital Insurance Transformation
Digital Insurance Transformation
 
Banking Chatbot
Banking ChatbotBanking Chatbot
Banking Chatbot
 
What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...
What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...
What is a Citizen Developer? How Can You Harness the Power of Citizen Develop...
 

Similar to Chatbots and AI

Module 8: Natural language processing Pt 1
Module 8:  Natural language processing Pt 1Module 8:  Natural language processing Pt 1
Module 8: Natural language processing Pt 1
Sara Hooker
 
Big Data and Natural Language Processing
Big Data and Natural Language ProcessingBig Data and Natural Language Processing
Big Data and Natural Language Processing
Michel Bruley
 
Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...
Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...
Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...
Seattle Interactive Conference
 
The Future of Search: How Measuring Satisfaction Will Enhance Our Personal ...
The Future of Search:  How Measuring Satisfaction Will  Enhance Our Personal ...The Future of Search:  How Measuring Satisfaction Will  Enhance Our Personal ...
The Future of Search: How Measuring Satisfaction Will Enhance Our Personal ...
teamozlo
 
Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016
Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016
Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016
teamozlo
 
Deep Learning for Dialogue Modeling - NTHU
Deep Learning for Dialogue Modeling - NTHUDeep Learning for Dialogue Modeling - NTHU
Deep Learning for Dialogue Modeling - NTHU
Yun-Nung (Vivian) Chen
 
NLP(Natural Language Processing)
NLP(Natural Language Processing)NLP(Natural Language Processing)
NLP(Natural Language Processing)
Jitendra Kumar Yadav
 
NLP - updated (Natural Language Processing))
NLP - updated (Natural Language Processing))NLP - updated (Natural Language Processing))
NLP - updated (Natural Language Processing))
Jitendra Kumar Yadav
 
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA International
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
punedevscom
 
From Natural Language Processing to Artificial Intelligence
From Natural Language Processing to Artificial IntelligenceFrom Natural Language Processing to Artificial Intelligence
From Natural Language Processing to Artificial Intelligence
Jonathan Mugan
 
Artificial Intelligence (Unit - 2).pdf
Artificial Intelligence   (Unit  -  2).pdfArtificial Intelligence   (Unit  -  2).pdf
Artificial Intelligence (Unit - 2).pdf
SathyaNarayanan47813
 
Natural Language Processing for development
Natural Language Processing for developmentNatural Language Processing for development
Natural Language Processing for development
Aravind Reddy
 
Natural Language Processing for development
Natural Language Processing for developmentNatural Language Processing for development
Natural Language Processing for development
Aravind Reddy
 
Deep Learning for Dialogue Systems
Deep Learning for Dialogue SystemsDeep Learning for Dialogue Systems
Deep Learning for Dialogue Systems
Yun-Nung (Vivian) Chen
 
What if-your-application-could-speak, by Marcos Silveira
What if-your-application-could-speak, by Marcos SilveiraWhat if-your-application-could-speak, by Marcos Silveira
What if-your-application-could-speak, by Marcos Silveira
Thoughtworks
 
What if-your-application-could-speak
What if-your-application-could-speakWhat if-your-application-could-speak
What if-your-application-could-speak
Marcos Vinícius
 
Making Websites Talk: the rise of Voice Search and Conversational Interfaces
Making Websites Talk: the rise of Voice Search and Conversational InterfacesMaking Websites Talk: the rise of Voice Search and Conversational Interfaces
Making Websites Talk: the rise of Voice Search and Conversational Interfaces
Andrea Volpini
 
Conversational experience by Systango
Conversational experience by SystangoConversational experience by Systango
Conversational experience by Systango
Systango
 
phrase autocomplete : Context completion auto-suggestor for real estate domain
phrase autocomplete : Context completion auto-suggestor for real estate domainphrase autocomplete : Context completion auto-suggestor for real estate domain
phrase autocomplete : Context completion auto-suggestor for real estate domain
Dhwaj Raj
 

Similar to Chatbots and AI (20)

Module 8: Natural language processing Pt 1
Module 8:  Natural language processing Pt 1Module 8:  Natural language processing Pt 1
Module 8: Natural language processing Pt 1
 
Big Data and Natural Language Processing
Big Data and Natural Language ProcessingBig Data and Natural Language Processing
Big Data and Natural Language Processing
 
Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...
Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...
Heidi Young - The Future of Search: How Measuring Satisfaction Will Enhance O...
 
The Future of Search: How Measuring Satisfaction Will Enhance Our Personal ...
The Future of Search:  How Measuring Satisfaction Will  Enhance Our Personal ...The Future of Search:  How Measuring Satisfaction Will  Enhance Our Personal ...
The Future of Search: How Measuring Satisfaction Will Enhance Our Personal ...
 
Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016
Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016
Heidi Young, Ozlo VP of Engineering, Seattle Interactive 2016
 
Deep Learning for Dialogue Modeling - NTHU
Deep Learning for Dialogue Modeling - NTHUDeep Learning for Dialogue Modeling - NTHU
Deep Learning for Dialogue Modeling - NTHU
 
NLP(Natural Language Processing)
NLP(Natural Language Processing)NLP(Natural Language Processing)
NLP(Natural Language Processing)
 
NLP - updated (Natural Language Processing))
NLP - updated (Natural Language Processing))NLP - updated (Natural Language Processing))
NLP - updated (Natural Language Processing))
 
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
UXPA2019 Not Your Average Chatbot: Using Cognitive Intercept to Improve Infor...
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 
From Natural Language Processing to Artificial Intelligence
From Natural Language Processing to Artificial IntelligenceFrom Natural Language Processing to Artificial Intelligence
From Natural Language Processing to Artificial Intelligence
 
Artificial Intelligence (Unit - 2).pdf
Artificial Intelligence   (Unit  -  2).pdfArtificial Intelligence   (Unit  -  2).pdf
Artificial Intelligence (Unit - 2).pdf
 
Natural Language Processing for development
Natural Language Processing for developmentNatural Language Processing for development
Natural Language Processing for development
 
Natural Language Processing for development
Natural Language Processing for developmentNatural Language Processing for development
Natural Language Processing for development
 
Deep Learning for Dialogue Systems
Deep Learning for Dialogue SystemsDeep Learning for Dialogue Systems
Deep Learning for Dialogue Systems
 
What if-your-application-could-speak, by Marcos Silveira
What if-your-application-could-speak, by Marcos SilveiraWhat if-your-application-could-speak, by Marcos Silveira
What if-your-application-could-speak, by Marcos Silveira
 
What if-your-application-could-speak
What if-your-application-could-speakWhat if-your-application-could-speak
What if-your-application-could-speak
 
Making Websites Talk: the rise of Voice Search and Conversational Interfaces
Making Websites Talk: the rise of Voice Search and Conversational InterfacesMaking Websites Talk: the rise of Voice Search and Conversational Interfaces
Making Websites Talk: the rise of Voice Search and Conversational Interfaces
 
Conversational experience by Systango
Conversational experience by SystangoConversational experience by Systango
Conversational experience by Systango
 
phrase autocomplete : Context completion auto-suggestor for real estate domain
phrase autocomplete : Context completion auto-suggestor for real estate domainphrase autocomplete : Context completion auto-suggestor for real estate domain
phrase autocomplete : Context completion auto-suggestor for real estate domain
 

More from Chatbots Paris

PocketConfidant chatbot
PocketConfidant chatbot PocketConfidant chatbot
PocketConfidant chatbot
Chatbots Paris
 
Conversational AI for Finance
Conversational AI for FinanceConversational AI for Finance
Conversational AI for Finance
Chatbots Paris
 
HelloJam
HelloJamHelloJam
HelloJam
Chatbots Paris
 
Les chatbots et la finance
Les chatbots et la financeLes chatbots et la finance
Les chatbots et la finance
Chatbots Paris
 
Chatbot Voyages SNCF
Chatbot Voyages SNCFChatbot Voyages SNCF
Chatbot Voyages SNCF
Chatbots Paris
 
1001 Pharmabot
1001 Pharmabot1001 Pharmabot
1001 Pharmabot
Chatbots Paris
 
Le commerce conversationnel, l'avenir du e-commerce
Le commerce conversationnel, l'avenir du e-commerceLe commerce conversationnel, l'avenir du e-commerce
Le commerce conversationnel, l'avenir du e-commerce
Chatbots Paris
 
6 months of experimentation with bots
6 months of experimentation with bots6 months of experimentation with bots
6 months of experimentation with bots
Chatbots Paris
 
Brands talk on Messenger
Brands talk on MessengerBrands talk on Messenger
Brands talk on Messenger
Chatbots Paris
 
Bot franceinfo
Bot franceinfoBot franceinfo
Bot franceinfo
Chatbots Paris
 
Chatbot Citron
Chatbot CitronChatbot Citron
Chatbot Citron
Chatbots Paris
 
Chatbots for HR
Chatbots for HRChatbots for HR
Chatbots for HR
Chatbots Paris
 
Chatbot
ChatbotChatbot
Creative chatbots
Creative chatbotsCreative chatbots
Creative chatbots
Chatbots Paris
 
Du chatbot au robot
Du chatbot au robotDu chatbot au robot
Du chatbot au robot
Chatbots Paris
 

More from Chatbots Paris (15)

PocketConfidant chatbot
PocketConfidant chatbot PocketConfidant chatbot
PocketConfidant chatbot
 
Conversational AI for Finance
Conversational AI for FinanceConversational AI for Finance
Conversational AI for Finance
 
HelloJam
HelloJamHelloJam
HelloJam
 
Les chatbots et la finance
Les chatbots et la financeLes chatbots et la finance
Les chatbots et la finance
 
Chatbot Voyages SNCF
Chatbot Voyages SNCFChatbot Voyages SNCF
Chatbot Voyages SNCF
 
1001 Pharmabot
1001 Pharmabot1001 Pharmabot
1001 Pharmabot
 
Le commerce conversationnel, l'avenir du e-commerce
Le commerce conversationnel, l'avenir du e-commerceLe commerce conversationnel, l'avenir du e-commerce
Le commerce conversationnel, l'avenir du e-commerce
 
6 months of experimentation with bots
6 months of experimentation with bots6 months of experimentation with bots
6 months of experimentation with bots
 
Brands talk on Messenger
Brands talk on MessengerBrands talk on Messenger
Brands talk on Messenger
 
Bot franceinfo
Bot franceinfoBot franceinfo
Bot franceinfo
 
Chatbot Citron
Chatbot CitronChatbot Citron
Chatbot Citron
 
Chatbots for HR
Chatbots for HRChatbots for HR
Chatbots for HR
 
Chatbot
ChatbotChatbot
Chatbot
 
Creative chatbots
Creative chatbotsCreative chatbots
Creative chatbots
 
Du chatbot au robot
Du chatbot au robotDu chatbot au robot
Du chatbot au robot
 

Recently uploaded

SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
UiPathCommunity
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
Pierluigi Pugliese
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
Sri Ambati
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
Elena Simperl
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
Safe Software
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
ViralQR
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
Thijs Feryn
 

Recently uploaded (20)

SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024By Design, not by Accident - Agile Venture Bolzano 2024
By Design, not by Accident - Agile Venture Bolzano 2024
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
GenAISummit 2024 May 28 Sri Ambati Keynote: AGI Belongs to The Community in O...
 
When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...When stars align: studies in data quality, knowledge graphs, and machine lear...
When stars align: studies in data quality, knowledge graphs, and machine lear...
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdfFIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
FIDO Alliance Osaka Seminar: FIDO Security Aspects.pdf
 
Essentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with ParametersEssentials of Automations: Optimizing FME Workflows with Parameters
Essentials of Automations: Optimizing FME Workflows with Parameters
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.Welocme to ViralQR, your best QR code generator.
Welocme to ViralQR, your best QR code generator.
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Accelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish CachingAccelerate your Kubernetes clusters with Varnish Caching
Accelerate your Kubernetes clusters with Varnish Caching
 

Chatbots and AI

  • 3. NOT WHAT CONVERSATION IS ABOUT SCRIPTED CHATBOTS
  • 4. A BIT DECEPTIVE SO FAR? AI BOTS Vertical vs Horizontal bots
  • 5. IT’S NOT ABOUT DEEP LEARNING ONLY AI ML NLP DL Expert systems Grammars ARTIFICIAL INTELLIGENCE ACHIEVEMENTS RL
  • 6. ANATOMY OF A BOT Natural Language Under- standing “I haven’t received my shoes I ordered last week” Intent: Delivery problem Product: Shoes Date: Last_week INPUT Dialog system Business logic TRANSFORMATION INTO STRUCTURED DATA Action: Indicate delivery status Delivery date: Tomorrow Reason for delay: Shortage Natural language generation Parse the input of the user to extract the meaning behind it, ideally observing context FETCHING RESULTS FROM BACKEND SERVICES Provide information, insights and functionality from the input FORMULATE ANSWER Organize information in a coherent, readable format “We are sorry. There was a shortage on these shoes. You will receive them tomorrow” OUTPUT HOW AI CAN HELP WITH CHATBOTS THOUGH?
  • 7. MACHINE LEARNING FOR NLP VR AND TEXT TO SPEECH POS TAGGING SENTIMENT ANALYSIS NATURAL LANGUAGE GENERATION MACHINE TRANSLATION DEPENDENCY PARSING ALREADY MANY ACHIEVEMENTS
  • 8. TEXT NEEDS CONTEXT Cat Kitten Mat? Discrete atomic symbols THE PROBLEM WITH TEXT
  • 9. EMBEDDINGS How words and sentences can be turned into numbers that machines can work with
  • 10. BACKGROUND Recent but successful technique Unsupervisedly learned word embeddings have been exceptionally successful in many NLP tasks. Maybe the primary reason for NLP's breakout. Encoding general semantic relationships Beneficial to many downstream tasks Distributional hypothesis Words that are used and occur in the same contexts tend to purport similar meanings.
  • 11. VECTOR SPACE MODELS 0 1 0 0 1 0 0 0 0 0 0 0 2 0 1 0Cat
  • 12. VECTOR SPACE MODELS 0 1 0 0 1 0 0 0 0 0 2 0 1 0Cat Doc2 Doc5 Doc11 Doc13 Could be word counts in documents
  • 13. VECTOR SPACE MODELS 0 1 0 0 1 0 0 0 0 0 1 0 1 0 cat cute drinks milk Bag of words, frequency count Bi-grams …. N-grams my cat is so cute when he drinks milk
  • 14. EMBEDDINGS Vectors discussed so far are very high dimensional Techniques used to learn lower-dimensional vectors are called embeddings
  • 15. LEARNING DENSE EMBEDDINGS Matrix factorization Glove, 2014 Shallow Neural Networks Word2Vec, 2013
  • 16. MAIN ADVANTAGES ● One of the few currently successful applications of unsupervised learning. ● Can be derived from large sets of unannotated corpora ● Pre-trained embeddings can then be used in downstream tasks that use small amounts of labeled data.
  • 17. WHAT CAN BE ACHIEVED?
  • 23. INTENT CLASSIFICATION Word embeddings are especially helpful when there is little training data I will travel to New York tomorrow I will leave for New York tomorrow I will take a flight to New York tomorrow {intent: travel}
  • 24. ENTITY RECOGNITION Do you know a good vietnamese restaurant? {restaurant_types: [italian french, japanese]} {restaurant_type: vietnamese}
  • 25. SOME REFERENCES Mikolov, T., Corrado, G., Chen, K., & Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. Proceedings of the International Conference on Learning Representations (ICLR 2013), 1–12. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Distributed Representations of Words and Phrases and their Compositionality. NIPS, 1–9. Bootstrapping Dialog Systems with Word Embeddings https://www.cs.cmu.edu/~apparikh/nips2014ml-nlp/camera-ready/forgues_e tal_mlnlp2014.pdf https://www.npmjs.com/package/word2vec https://radimrehurek.com/gensim/
  • 26. TELL US WHICH BOT YOU NEED, WE MOST PROBABLY KNOW HOW TO DO IT Web http://botfuel.io E-mail sales@botfuel.io Fueling the next generation of bots