SlideShare a Scribd company logo
© 2011 IBM Corporation© 2011 IBM Corporation
Building Watson
A Brief Overview of the Jeopardy! Challenge
Dr. Mark Sherman
IBM Software Group Strategy
© 2011 IBM Corporation
 Capture the imagination
– The Next Deep Blue
 Engage the scientific community
– Envision new ways for computers to impact society & science
– Drive important and measurable scientific advances
 Be Relevant to IBM Customers
– Enable better, faster decision making
– Business Intelligence, Knowledge Discovery and Management, Government,
Compliance, Publishing, Legal, Healthcare, Business Integrity, Customer
Relationship Management, Web Self-Service, Product Support, etc.
A Grand Challenge Opportunity
2
© 2011 IBM Corporation
Informed Decision Making: Search vs. Expert Q&A
Decision Maker
Search Engine
Finds Documents containing Keywords
Delivers Documents based on Popularity
Has Question
Distills to 2-3 Keywords
Reads Documents, Finds
Answers
Finds & Analyzes Evidence
© 2011 IBM Corporation
Informed Decision Making: Search vs. Expert Q&A
Expert
Understands Question
Produces Possible Answers & Evidence
Delivers Response, Evidence & Confidence
Analyzes Evidence, Computes Confidence
Asks NL Question
Considers Answer & Evidence
Decision Maker
© 2011 IBM Corporation
Informed Decision Making: Search vs. Expert Q&A
Decision Maker
Search Engine
Finds Documents containing Keywords
Delivers Documents based on Popularity
Has Question
Distills to 2-3 Keywords
Reads Documents, Finds
Answers
Finds & Analyzes Evidence
Expert
Understands Question
Produces Possible Answers & Evidence
Delivers Response, Evidence & Confidence
Analyzes Evidence, Computes Confidence
Asks NL Question
Considers Answer & Evidence
Decision Maker
© 2011 IBM Corporation6
Broad Domain
Our Focus is on reusable NLP technology for analyzing vast volumes of as-is text.
Structured sources (DBs and KBs) provide background knowledge for interpreting the text.
We do NOT attempt to anticipate all
questions and build databases.
In a random sample of 20,000 questions we found
2,500 distinct types*. The most frequent occurring <3% of the time.
The distribution has a very long tail.
And for each these types 1000’s of different things may be asked.
*13% are non-distinct (e.g, it, this, these or NA)
Even going for the head of the tail will
barely make a dent
We do NOT try to build a formal
model of the world
© 2011 IBM Corporation7
What It Takes to compete against Top Human Jeopardy! Players
Our Analysis Reveals the Winner’s Cloud
Winning Human
Performance
Winning Human
Performance
Grand Champion
Human Performance
Grand Champion
Human Performance
Each dot – actual historical human Jeopardy! games
More ConfidentMore Confident Less ConfidentLess Confident
© 2011 IBM Corporation8
What It Takes to compete against Top Human Jeopardy! Players
Our Analysis Reveals the Winner’s Cloud
Winning Human
Performance
Winning Human
Performance
2007 QA Computer System2007 QA Computer System
Grand Champion
Human Performance
Grand Champion
Human Performance
Each dot – actual historical human Jeopardy! games
More ConfidentMore Confident Less ConfidentLess Confident
Computers?
Not So Good.
© 2011 IBM Corporation
Baseline
v0.1 12/07
v0.3 08/08
v0.5 05/09
v0.6 10/09
v0.7 04/10
v0.4 12/08
DeepQA: Incremental Progress in Answering Precision: 6/2007-4/2010
v0.2 05/08
© 2011 IBM Corporation
One Jeopardy! question can take 2 hours on a single 2.6Ghz Core
Optimized & Scaled out on 2880-Core IBM HPC using UIMA-AS,
Watson is answering in 2-6 seconds.
Question
100s Possible
Answers
1000’s of
Pieces of Evidence
Multiple
Interpretations
100,000’s scores from many simultaneous
Text Analysis Algorithms100s sources
. . .
Hypothesis
Generation
Hypothesis and
Evidence Scoring
Final Confidence
Merging &
Ranking
Synthesis
Question &
Topic
Analysis
Question
Decomposition
Hypothesis
Generation
Hypothesis and Evidence
Scoring
Answer &
Confidence
© 2011 IBM Corporation
Potential Business Applications
Tech Support: Help-desk, Contact Centers
Healthcare / Life Sciences: Diagnostic Assistance, Evidenced-
Based, Collaborative Medicine
Enterprise Knowledge Management and Business
Intelligence
Government: Improved Information Sharing
and Security
© 2011 IBM Corporation
The Core Technical Team
Researchers and Engineers in NLP, ML, IR, KR&R and CL at
IBM Labs and a growing number of universities
© 2011 IBM Corporation
THANK YOU

More Related Content

Similar to CMU 2011 Watson Event

IBM Watson-How it works
IBM Watson-How it worksIBM Watson-How it works
IBM Watson-How it works
Virginia Fernandez
 
Watson how it works?
Watson how it works?Watson how it works?
Watson how it works?
Ana Alves Sequeira
 
Ibm watson - how it works, and what it means for society beyond winning jeo...
Ibm   watson - how it works, and what it means for society beyond winning jeo...Ibm   watson - how it works, and what it means for society beyond winning jeo...
Ibm watson - how it works, and what it means for society beyond winning jeo...
Rick Bouter
 
Enterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challengesEnterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challenges
Yunyao Li
 
Value proposition for big data isv partners 0714
Value proposition for big data isv partners 0714Value proposition for big data isv partners 0714
Value proposition for big data isv partners 0714Niu Bai
 
Predicitve analytics for marketing 05 21-2014 Shree Dandekar
Predicitve analytics for marketing 05 21-2014 Shree DandekarPredicitve analytics for marketing 05 21-2014 Shree Dandekar
Predicitve analytics for marketing 05 21-2014 Shree Dandekar
Shree Dandekar
 
Cashing In On Lead Conversion
Cashing In On Lead ConversionCashing In On Lead Conversion
Cashing In On Lead Conversion
Jonathan D Nicholas
 
How Can I Make My College Essay Stand Out
How Can I Make My College Essay Stand OutHow Can I Make My College Essay Stand Out
How Can I Make My College Essay Stand Out
Heidi Maestas
 
ConnXus myCBC Webinar Series: Cybersecurity Risks to Your Business
ConnXus myCBC Webinar Series: Cybersecurity Risks to Your BusinessConnXus myCBC Webinar Series: Cybersecurity Risks to Your Business
ConnXus myCBC Webinar Series: Cybersecurity Risks to Your Business
ConnXus
 
WCR Summit: Cashing In On Lead Conversion
WCR Summit: Cashing In On Lead ConversionWCR Summit: Cashing In On Lead Conversion
WCR Summit: Cashing In On Lead Conversion
Jonathan D Nicholas
 
Innovation and punditry_web_2.0_final
Innovation and punditry_web_2.0_finalInnovation and punditry_web_2.0_final
Innovation and punditry_web_2.0_final
Glenn Klith Andersen
 
Flagstaff chamber keynote presentation
Flagstaff chamber keynote presentationFlagstaff chamber keynote presentation
Flagstaff chamber keynote presentation
Data Doctors
 
Lynn wong: make a difference with big data - HP
Lynn wong: make a difference with big data - HPLynn wong: make a difference with big data - HP
Lynn wong: make a difference with big data - HP
Vu Hung Nguyen
 
Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...
Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...
Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...
Jason Hong
 
Tech M&A Forecast 2011
Tech M&A Forecast 2011Tech M&A Forecast 2011
Tech M&A Forecast 2011
Alina Soltys
 
IW14 Session: Mike Gualtieri, Forrester Research
IW14 Session: Mike Gualtieri, Forrester ResearchIW14 Session: Mike Gualtieri, Forrester Research
IW14 Session: Mike Gualtieri, Forrester Research
Software AG
 
Don't Invest in Enterprise Data, Unless...
Don't Invest in Enterprise Data, Unless...Don't Invest in Enterprise Data, Unless...
Don't Invest in Enterprise Data, Unless...
Embarcadero Technologies
 

Similar to CMU 2011 Watson Event (20)

IBM Watson-How it works
IBM Watson-How it worksIBM Watson-How it works
IBM Watson-How it works
 
Watson how it works?
Watson how it works?Watson how it works?
Watson how it works?
 
Ibm watson - how it works, and what it means for society beyond winning jeo...
Ibm   watson - how it works, and what it means for society beyond winning jeo...Ibm   watson - how it works, and what it means for society beyond winning jeo...
Ibm watson - how it works, and what it means for society beyond winning jeo...
 
DAMA Big Data & The Cloud 2012-01-19
DAMA Big Data & The Cloud 2012-01-19DAMA Big Data & The Cloud 2012-01-19
DAMA Big Data & The Cloud 2012-01-19
 
CTAM Making Analytics Actionable RJA FINAL
CTAM Making Analytics Actionable RJA FINALCTAM Making Analytics Actionable RJA FINAL
CTAM Making Analytics Actionable RJA FINAL
 
Enterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challengesEnterprise information extraction: recent developments and open challenges
Enterprise information extraction: recent developments and open challenges
 
Value proposition for big data isv partners 0714
Value proposition for big data isv partners 0714Value proposition for big data isv partners 0714
Value proposition for big data isv partners 0714
 
Predicitve analytics for marketing 05 21-2014 Shree Dandekar
Predicitve analytics for marketing 05 21-2014 Shree DandekarPredicitve analytics for marketing 05 21-2014 Shree Dandekar
Predicitve analytics for marketing 05 21-2014 Shree Dandekar
 
Cashing In On Lead Conversion
Cashing In On Lead ConversionCashing In On Lead Conversion
Cashing In On Lead Conversion
 
How Can I Make My College Essay Stand Out
How Can I Make My College Essay Stand OutHow Can I Make My College Essay Stand Out
How Can I Make My College Essay Stand Out
 
ConnXus myCBC Webinar Series: Cybersecurity Risks to Your Business
ConnXus myCBC Webinar Series: Cybersecurity Risks to Your BusinessConnXus myCBC Webinar Series: Cybersecurity Risks to Your Business
ConnXus myCBC Webinar Series: Cybersecurity Risks to Your Business
 
WCR Summit: Cashing In On Lead Conversion
WCR Summit: Cashing In On Lead ConversionWCR Summit: Cashing In On Lead Conversion
WCR Summit: Cashing In On Lead Conversion
 
Innovation and punditry_web_2.0_final
Innovation and punditry_web_2.0_finalInnovation and punditry_web_2.0_final
Innovation and punditry_web_2.0_final
 
Flagstaff chamber keynote presentation
Flagstaff chamber keynote presentationFlagstaff chamber keynote presentation
Flagstaff chamber keynote presentation
 
Lynn wong: make a difference with big data - HP
Lynn wong: make a difference with big data - HPLynn wong: make a difference with big data - HP
Lynn wong: make a difference with big data - HP
 
Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...
Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...
Leveraging Human Factors for Effective Security Training, for ISSA Webinar Ma...
 
CIO Strategies 2008
CIO Strategies 2008CIO Strategies 2008
CIO Strategies 2008
 
Tech M&A Forecast 2011
Tech M&A Forecast 2011Tech M&A Forecast 2011
Tech M&A Forecast 2011
 
IW14 Session: Mike Gualtieri, Forrester Research
IW14 Session: Mike Gualtieri, Forrester ResearchIW14 Session: Mike Gualtieri, Forrester Research
IW14 Session: Mike Gualtieri, Forrester Research
 
Don't Invest in Enterprise Data, Unless...
Don't Invest in Enterprise Data, Unless...Don't Invest in Enterprise Data, Unless...
Don't Invest in Enterprise Data, Unless...
 

Recently uploaded

AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
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: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
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
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Product School
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
Guy Korland
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
Abida Shariff
 
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
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 
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
 
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
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
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
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
DanBrown980551
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
Alison B. Lowndes
 
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
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
Fwdays
 

Recently uploaded (20)

AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
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: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
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
 
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
 
GraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge GraphGraphRAG is All You need? LLM & Knowledge Graph
GraphRAG is All You need? LLM & Knowledge Graph
 
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 
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
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 
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
 
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
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
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...
 
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
LF Energy Webinar: Electrical Grid Modelling and Simulation Through PowSyBl -...
 
Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........Bits & Pixels using AI for Good.........
Bits & Pixels using AI for Good.........
 
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)
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi"Impact of front-end architecture on development cost", Viktor Turskyi
"Impact of front-end architecture on development cost", Viktor Turskyi
 

CMU 2011 Watson Event

  • 1. © 2011 IBM Corporation© 2011 IBM Corporation Building Watson A Brief Overview of the Jeopardy! Challenge Dr. Mark Sherman IBM Software Group Strategy
  • 2. © 2011 IBM Corporation  Capture the imagination – The Next Deep Blue  Engage the scientific community – Envision new ways for computers to impact society & science – Drive important and measurable scientific advances  Be Relevant to IBM Customers – Enable better, faster decision making – Business Intelligence, Knowledge Discovery and Management, Government, Compliance, Publishing, Legal, Healthcare, Business Integrity, Customer Relationship Management, Web Self-Service, Product Support, etc. A Grand Challenge Opportunity 2
  • 3. © 2011 IBM Corporation Informed Decision Making: Search vs. Expert Q&A Decision Maker Search Engine Finds Documents containing Keywords Delivers Documents based on Popularity Has Question Distills to 2-3 Keywords Reads Documents, Finds Answers Finds & Analyzes Evidence
  • 4. © 2011 IBM Corporation Informed Decision Making: Search vs. Expert Q&A Expert Understands Question Produces Possible Answers & Evidence Delivers Response, Evidence & Confidence Analyzes Evidence, Computes Confidence Asks NL Question Considers Answer & Evidence Decision Maker
  • 5. © 2011 IBM Corporation Informed Decision Making: Search vs. Expert Q&A Decision Maker Search Engine Finds Documents containing Keywords Delivers Documents based on Popularity Has Question Distills to 2-3 Keywords Reads Documents, Finds Answers Finds & Analyzes Evidence Expert Understands Question Produces Possible Answers & Evidence Delivers Response, Evidence & Confidence Analyzes Evidence, Computes Confidence Asks NL Question Considers Answer & Evidence Decision Maker
  • 6. © 2011 IBM Corporation6 Broad Domain Our Focus is on reusable NLP technology for analyzing vast volumes of as-is text. Structured sources (DBs and KBs) provide background knowledge for interpreting the text. We do NOT attempt to anticipate all questions and build databases. In a random sample of 20,000 questions we found 2,500 distinct types*. The most frequent occurring <3% of the time. The distribution has a very long tail. And for each these types 1000’s of different things may be asked. *13% are non-distinct (e.g, it, this, these or NA) Even going for the head of the tail will barely make a dent We do NOT try to build a formal model of the world
  • 7. © 2011 IBM Corporation7 What It Takes to compete against Top Human Jeopardy! Players Our Analysis Reveals the Winner’s Cloud Winning Human Performance Winning Human Performance Grand Champion Human Performance Grand Champion Human Performance Each dot – actual historical human Jeopardy! games More ConfidentMore Confident Less ConfidentLess Confident
  • 8. © 2011 IBM Corporation8 What It Takes to compete against Top Human Jeopardy! Players Our Analysis Reveals the Winner’s Cloud Winning Human Performance Winning Human Performance 2007 QA Computer System2007 QA Computer System Grand Champion Human Performance Grand Champion Human Performance Each dot – actual historical human Jeopardy! games More ConfidentMore Confident Less ConfidentLess Confident Computers? Not So Good.
  • 9. © 2011 IBM Corporation Baseline v0.1 12/07 v0.3 08/08 v0.5 05/09 v0.6 10/09 v0.7 04/10 v0.4 12/08 DeepQA: Incremental Progress in Answering Precision: 6/2007-4/2010 v0.2 05/08
  • 10. © 2011 IBM Corporation One Jeopardy! question can take 2 hours on a single 2.6Ghz Core Optimized & Scaled out on 2880-Core IBM HPC using UIMA-AS, Watson is answering in 2-6 seconds. Question 100s Possible Answers 1000’s of Pieces of Evidence Multiple Interpretations 100,000’s scores from many simultaneous Text Analysis Algorithms100s sources . . . Hypothesis Generation Hypothesis and Evidence Scoring Final Confidence Merging & Ranking Synthesis Question & Topic Analysis Question Decomposition Hypothesis Generation Hypothesis and Evidence Scoring Answer & Confidence
  • 11. © 2011 IBM Corporation Potential Business Applications Tech Support: Help-desk, Contact Centers Healthcare / Life Sciences: Diagnostic Assistance, Evidenced- Based, Collaborative Medicine Enterprise Knowledge Management and Business Intelligence Government: Improved Information Sharing and Security
  • 12. © 2011 IBM Corporation The Core Technical Team Researchers and Engineers in NLP, ML, IR, KR&R and CL at IBM Labs and a growing number of universities
  • 13. © 2011 IBM Corporation THANK YOU