SlideShare une entreprise Scribd logo
1  sur  27
Télécharger pour lire hors ligne
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. 7/17/2015
Deep QA (Question/Answer)
Lessons From Watson and Jeopardy!
October 13, 2016
Adrian Bowles, PhD
Founder, STORM Insights, Inc.
info@storminsights.com
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Deep Question/Answering - Lessons from Watson & Jeopardy!
The Game
The Challenge
Scope of the problem
DeepQA Architecture & Processes
Software, Hardware & Resources
Next Steps
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Answers must be given in the form of a question
Last contestant to answer correctly chooses the next question
Correct responses must satisfy the demands of both the clue and the
category
Jeopardy
Six categories, 5 Questions for each category, $100-500 based on
difficulty
Double Jeopardy
Six categories, 5 Questions for each category, $200-1,000 based on
difficulty, and 3 hidden questions allow the person who chooses them to
bet everything they have at that point in the game
Final Jeopardy
Player must have a positive balance from the previous round to play
Players see the category and then decide - secretly - how much to wager
The question is presented
30 seconds to answer
Playing the Game:
Wikipedia, The Free Encyclopedia. October 12, 2016, 02:40 UTC.
Available at: https://en.wikipedia.org/w/index.php?title=Jeopardy!&oldid=743931483. Accessed October 12, 2016.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Open Domain, broad use of language - Jeopardy! questions often involve puns, ambiguity…
IBM reviewed a sample of 20,000 questions, and found 2,500 distinct lexical answer types (LA
No single LAT accounted for more than 3% of the total
For each category, there could be thousands of questions
Best players provide correct answers ~85% of the time
Best players know what they don’t know - base their bets on their confidence
~3 seconds to answer questions
Challenges of Jeopardy! for Machines:
Players may only use the data/knowledge they have on arrival - no lifelines, resources…
Constraint
Winning Jeopardy! requires a contestant to answer
~70% of the questions, with 80%+ precision.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Predicting lexical answer types in open domain question and answering (qa) systems
US 20130035931 A1 2013, Ferrucci, Gliozzo, Kalyanpur
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Precisio
n
Speed
Confide
nce
Quality
SpeedCost
Business Constraints Jeopardy! Constraints
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Look for Similar
Solved
Problems
Accept or Create
Problem Statement
Generate
Hypotheses
Identify Evidence
in Corpus
Score
Evidence
Score
Hypotheses
Present
Results
Get
Feedback
Train
ModelOrientAct
Observe
Decide
World
Model
Formalizing the Decision-Making Process
Boyd’s Loop
John Boyd (1927-
1997)
Continuous Learning
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Machine
Learning
NLU NLG
Informatio
n
Retrieval
Reasoning
Knowledge
Represent
ation
Evidence
Gather Decide
Evaluate Weigh
Generate
Hypothese
s
Automating QA
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
* Building Watson: An Overview of the DeepQA Project, AI Magazine, Fall 2010 Issue,
Ferrucci, Brown, Chu-Carroll, Fan, Gondek, Kalyanpur, Lally, Murdock, Nyberg, Prager, Schlaefer, Welty.
Build a database of question/answer pairs
Build a formal model of the world
Build a search engine
What they didn’t do:
What they did:
DeepQA - “a massively parallel probabalistic evidence-based architecture.”*
Develop reusable NLU tech to analyze text
Analyze sources - structured and unstructured - to capture background knowledge
Apply knowledge representation and Reasoning (KRR) to the resulting structured knowledge
Use machine learning to generate and score hypotheses
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Massively Parallel Probabalistic Evidence-based Architecture
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Content Acquisition
Building the corpus
For Jeopardy! this had to be
completed before the game
commenced.
Ingested encyclopedias,
dictionaries, thesauri,
newswire articles, literary
works, databases,
taxonomies, ontologies…
IRL, we can identify and use new resources
based on the problem at hand.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Question Analysis
What is being asked?
Question classification:
any words with double
meanings?
Puzzle question, factoid…?
Detect
focus
LAT
relations
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Relation-detection
“They’re the two states you could be reentering if
you’re crossing Florida’s norther border.”
Category: Head North
borders(Florida, ?,x,north)
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Hypothesis Generation
& Scoring
Use a candidate answer with the
question, try to prove correct with
a degree of confidence supported
by the evidence.
Scoring may use a variety of
relationships:
temporal
spatial
geospatial
taxonomic classification
correlation between candidate
and question…
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Evaluating Potential Answers
Watson scores evidence in
multiple dimensions
What works for a factoid question
may not work for a puzzle question.
“Chile shares its longest
land border with this country.”
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Merging & Ranking
Identifying the most likely
answer based on confidence
scores.
Answer scores are merged
before ranking and
confidence estimation.
Uses ML approach to
compare with training set
data when confidence scores
in different categories result
in “too close to call” results.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Wikipedia, The Free Encyclopedia. October 12, 2016, 17:06 UTC.
Available at: https://en.wikipedia.org/w/index.php?title=Watson_(computer)&oldid=744021754. Accessed October 12, 2016.
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Software
Apache Hadoop
http://hadoop.apache.org
Apache UIMA - Unstructured
Information Management
Architecture
http://uima.apache.org
IBM DB2
Linux (Suse Enterprise Server 11)
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Resources
Wordnet(R) Princeton University "About WordNet." WordNet.
Princeton University. 2010. <http://wordnet.princeton.edu>
Wordnet(R)
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Resources
Wordnet(R) Princeton University "About WordNet."
WordNet. Princeton University. 2010.
<http://wordnet.princeton.edu>
Wordnet(R)
Copyright (c) 2016 by STORM Insights Inc. All Rights Reserved. 9/28/2011
IBM Power 750
90 servers, 32 cores/server,
2880 Cores in 10 racks
16Tb RAM
~80TeraFLOPS
80,000,000,000,000FLOPS
Hardware
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
Next Steps…
For more information:
Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
adrian@storminsights.com
Twitter @ajbowles
Skype ajbowles
Upcoming Webinar Dates & Topics
November 10 Emerging Hardware Choices for Modern AI Data Management
December 8 Leverage the IOT to Build a Smart Data Ecosystem
2017 Webinar Themes
Technology Trends
Market Trends
Communicating
Learning
Understanding
Reasoning
Planning

Contenu connexe

En vedette

REU Final PowerPoint
REU Final PowerPointREU Final PowerPoint
REU Final PowerPoint
Alyssa Castle
 
Programa de eventos
Programa de eventosPrograma de eventos
Programa de eventos
sebastian333
 
Grafico diario del dax perfomance index para el 11 07-2012
Grafico diario del dax perfomance index para el 11 07-2012Grafico diario del dax perfomance index para el 11 07-2012
Grafico diario del dax perfomance index para el 11 07-2012
Experiencia Trading
 
olenka flores gutierrez-el internet
olenka flores gutierrez-el internetolenka flores gutierrez-el internet
olenka flores gutierrez-el internet
pinquipay
 
ИНТЕРАКТИВНЫЙ ЖУРНАЛ
ИНТЕРАКТИВНЫЙ ЖУРНАЛИНТЕРАКТИВНЫЙ ЖУРНАЛ
ИНТЕРАКТИВНЫЙ ЖУРНАЛ
kulibin
 
Untitleddocument
UntitleddocumentUntitleddocument
Untitleddocument
beita1994
 

En vedette (19)

”宿”から”カフェ”へ
”宿”から”カフェ”へ”宿”から”カフェ”へ
”宿”から”カフェ”へ
 
Putting People First - Building and Sustaining Awesome Distributed Teams at S...
Putting People First - Building and Sustaining Awesome Distributed Teams at S...Putting People First - Building and Sustaining Awesome Distributed Teams at S...
Putting People First - Building and Sustaining Awesome Distributed Teams at S...
 
30 DAY CHALLENGE OF PTEASLIM - LOSS YOUR WEIGHT WITHING 30 DAYS.
30 DAY CHALLENGE OF PTEASLIM - LOSS YOUR WEIGHT WITHING 30 DAYS.30 DAY CHALLENGE OF PTEASLIM - LOSS YOUR WEIGHT WITHING 30 DAYS.
30 DAY CHALLENGE OF PTEASLIM - LOSS YOUR WEIGHT WITHING 30 DAYS.
 
REU Final PowerPoint
REU Final PowerPointREU Final PowerPoint
REU Final PowerPoint
 
Infographics for Fun and Profit DreamForce 2014
Infographics for Fun and Profit DreamForce 2014Infographics for Fun and Profit DreamForce 2014
Infographics for Fun and Profit DreamForce 2014
 
Rowing Travel as Club Development
Rowing Travel as Club DevelopmentRowing Travel as Club Development
Rowing Travel as Club Development
 
Tesis unidad anialisis fianciero disertacion tesis 2015 (2)
Tesis unidad anialisis fianciero disertacion tesis 2015 (2)Tesis unidad anialisis fianciero disertacion tesis 2015 (2)
Tesis unidad anialisis fianciero disertacion tesis 2015 (2)
 
Cash Center brochure
Cash Center brochureCash Center brochure
Cash Center brochure
 
ASCEND Content Marketing Power Tools
ASCEND Content Marketing Power ToolsASCEND Content Marketing Power Tools
ASCEND Content Marketing Power Tools
 
eDMs eCards & eNewsletters • Part 1
eDMs eCards & eNewsletters • Part 1eDMs eCards & eNewsletters • Part 1
eDMs eCards & eNewsletters • Part 1
 
Programa de eventos
Programa de eventosPrograma de eventos
Programa de eventos
 
Grafico diario del dax perfomance index para el 11 07-2012
Grafico diario del dax perfomance index para el 11 07-2012Grafico diario del dax perfomance index para el 11 07-2012
Grafico diario del dax perfomance index para el 11 07-2012
 
olenka flores gutierrez-el internet
olenka flores gutierrez-el internetolenka flores gutierrez-el internet
olenka flores gutierrez-el internet
 
TCC Metagame book club
TCC Metagame book clubTCC Metagame book club
TCC Metagame book club
 
ИНТЕРАКТИВНЫЙ ЖУРНАЛ
ИНТЕРАКТИВНЫЙ ЖУРНАЛИНТЕРАКТИВНЫЙ ЖУРНАЛ
ИНТЕРАКТИВНЫЙ ЖУРНАЛ
 
EPA CAA Email 10.4.03
EPA CAA Email 10.4.03EPA CAA Email 10.4.03
EPA CAA Email 10.4.03
 
Untitleddocument
UntitleddocumentUntitleddocument
Untitleddocument
 
Inventario
InventarioInventario
Inventario
 
Jpa 필드 와 컬럼 매핑 레퍼런스
Jpa 필드 와 컬럼 매핑 레퍼런스Jpa 필드 와 컬럼 매핑 레퍼런스
Jpa 필드 와 컬럼 매핑 레퍼런스
 

Similaire à Smart Data Webinar: Deep QA (Question/Answer) - Lessons From Watson and Jeopardy!

Big, Open, Data and Semantics for Real-World Application Near You
Big, Open, Data and Semantics for Real-World Application Near YouBig, Open, Data and Semantics for Real-World Application Near You
Big, Open, Data and Semantics for Real-World Application Near You
Biplav Srivastava
 
Sense and Sensors - From Perception to Personality
Sense and Sensors - From Perception to PersonalitySense and Sensors - From Perception to Personality
Sense and Sensors - From Perception to Personality
DATAVERSITY
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
butest
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
butest
 
A Philosophical Essay On Probabilities
A Philosophical Essay On ProbabilitiesA Philosophical Essay On Probabilities
A Philosophical Essay On Probabilities
Rebecca Harris
 

Similaire à Smart Data Webinar: Deep QA (Question/Answer) - Lessons From Watson and Jeopardy! (20)

Smart Data Webinar: Advances in Natural Language Processing
Smart Data Webinar: Advances in Natural Language ProcessingSmart Data Webinar: Advances in Natural Language Processing
Smart Data Webinar: Advances in Natural Language Processing
 
Smart Data Webinar: Emerging Data Management Options
Smart Data Webinar: Emerging Data Management OptionsSmart Data Webinar: Emerging Data Management Options
Smart Data Webinar: Emerging Data Management Options
 
Smart Data Webinar: Machine Learning (ML) Adoption Strategies
Smart Data Webinar: Machine Learning (ML) Adoption StrategiesSmart Data Webinar: Machine Learning (ML) Adoption Strategies
Smart Data Webinar: Machine Learning (ML) Adoption Strategies
 
Upmc tpdev7
Upmc tpdev7Upmc tpdev7
Upmc tpdev7
 
Java one2016 con3054-watsonap-is
Java one2016 con3054-watsonap-isJava one2016 con3054-watsonap-is
Java one2016 con3054-watsonap-is
 
Building Cognitive Applications with Watson APIs
Building Cognitive Applications with Watson APIs Building Cognitive Applications with Watson APIs
Building Cognitive Applications with Watson APIs
 
Java one2016 con3054-watsonap-is
Java one2016 con3054-watsonap-isJava one2016 con3054-watsonap-is
Java one2016 con3054-watsonap-is
 
Smart Data Webinar: A Roadmap for Deploying Modern AI in Business
Smart Data Webinar: A Roadmap for Deploying Modern AI in BusinessSmart Data Webinar: A Roadmap for Deploying Modern AI in Business
Smart Data Webinar: A Roadmap for Deploying Modern AI in Business
 
Big, Open, Data and Semantics for Real-World Application Near You
Big, Open, Data and Semantics for Real-World Application Near YouBig, Open, Data and Semantics for Real-World Application Near You
Big, Open, Data and Semantics for Real-World Application Near You
 
Sense and Sensors - From Perception to Personality
Sense and Sensors - From Perception to PersonalitySense and Sensors - From Perception to Personality
Sense and Sensors - From Perception to Personality
 
Meaningful User Experience
Meaningful User ExperienceMeaningful User Experience
Meaningful User Experience
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
 
Machine Learning ICS 273A
Machine Learning ICS 273AMachine Learning ICS 273A
Machine Learning ICS 273A
 
Smart Data - The Foundation for Better Business Outcomes
Smart Data - The Foundation for Better Business OutcomesSmart Data - The Foundation for Better Business Outcomes
Smart Data - The Foundation for Better Business Outcomes
 
Implementing Your Own Chatbot Platform!
Implementing Your Own Chatbot Platform!Implementing Your Own Chatbot Platform!
Implementing Your Own Chatbot Platform!
 
A Philosophical Essay On Probabilities
A Philosophical Essay On ProbabilitiesA Philosophical Essay On Probabilities
A Philosophical Essay On Probabilities
 
Machine Learning & Cyber Security: Detecting Malicious URLs in the Haystack
Machine Learning & Cyber Security: Detecting Malicious URLs in the HaystackMachine Learning & Cyber Security: Detecting Malicious URLs in the Haystack
Machine Learning & Cyber Security: Detecting Malicious URLs in the Haystack
 
The Ethics of AI
The Ethics of AIThe Ethics of AI
The Ethics of AI
 
Bsides Chicago2017
Bsides Chicago2017Bsides Chicago2017
Bsides Chicago2017
 
Smart Data Webinar: Organizing Data and Knowledge - The Role of Taxonomies an...
Smart Data Webinar: Organizing Data and Knowledge - The Role of Taxonomies an...Smart Data Webinar: Organizing Data and Knowledge - The Role of Taxonomies an...
Smart Data Webinar: Organizing Data and Knowledge - The Role of Taxonomies an...
 

Plus de DATAVERSITY

The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...
The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...
The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...
DATAVERSITY
 
Data Strategy Best Practices
Data Strategy Best PracticesData Strategy Best Practices
Data Strategy Best Practices
DATAVERSITY
 

Plus de DATAVERSITY (20)

Architecture, Products, and Total Cost of Ownership of the Leading Machine Le...
Architecture, Products, and Total Cost of Ownership of the Leading Machine Le...Architecture, Products, and Total Cost of Ownership of the Leading Machine Le...
Architecture, Products, and Total Cost of Ownership of the Leading Machine Le...
 
Data at the Speed of Business with Data Mastering and Governance
Data at the Speed of Business with Data Mastering and GovernanceData at the Speed of Business with Data Mastering and Governance
Data at the Speed of Business with Data Mastering and Governance
 
Exploring Levels of Data Literacy
Exploring Levels of Data LiteracyExploring Levels of Data Literacy
Exploring Levels of Data Literacy
 
Building a Data Strategy – Practical Steps for Aligning with Business Goals
Building a Data Strategy – Practical Steps for Aligning with Business GoalsBuilding a Data Strategy – Practical Steps for Aligning with Business Goals
Building a Data Strategy – Practical Steps for Aligning with Business Goals
 
Make Data Work for You
Make Data Work for YouMake Data Work for You
Make Data Work for You
 
Data Catalogs Are the Answer – What is the Question?
Data Catalogs Are the Answer – What is the Question?Data Catalogs Are the Answer – What is the Question?
Data Catalogs Are the Answer – What is the Question?
 
Data Catalogs Are the Answer – What Is the Question?
Data Catalogs Are the Answer – What Is the Question?Data Catalogs Are the Answer – What Is the Question?
Data Catalogs Are the Answer – What Is the Question?
 
Data Modeling Fundamentals
Data Modeling FundamentalsData Modeling Fundamentals
Data Modeling Fundamentals
 
Showing ROI for Your Analytic Project
Showing ROI for Your Analytic ProjectShowing ROI for Your Analytic Project
Showing ROI for Your Analytic Project
 
How a Semantic Layer Makes Data Mesh Work at Scale
How a Semantic Layer Makes  Data Mesh Work at ScaleHow a Semantic Layer Makes  Data Mesh Work at Scale
How a Semantic Layer Makes Data Mesh Work at Scale
 
Is Enterprise Data Literacy Possible?
Is Enterprise Data Literacy Possible?Is Enterprise Data Literacy Possible?
Is Enterprise Data Literacy Possible?
 
The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...
The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...
The Data Trifecta – Privacy, Security & Governance Race from Reactivity to Re...
 
Emerging Trends in Data Architecture – What’s the Next Big Thing?
Emerging Trends in Data Architecture – What’s the Next Big Thing?Emerging Trends in Data Architecture – What’s the Next Big Thing?
Emerging Trends in Data Architecture – What’s the Next Big Thing?
 
Data Governance Trends - A Look Backwards and Forwards
Data Governance Trends - A Look Backwards and ForwardsData Governance Trends - A Look Backwards and Forwards
Data Governance Trends - A Look Backwards and Forwards
 
Data Governance Trends and Best Practices To Implement Today
Data Governance Trends and Best Practices To Implement TodayData Governance Trends and Best Practices To Implement Today
Data Governance Trends and Best Practices To Implement Today
 
2023 Trends in Enterprise Analytics
2023 Trends in Enterprise Analytics2023 Trends in Enterprise Analytics
2023 Trends in Enterprise Analytics
 
Data Strategy Best Practices
Data Strategy Best PracticesData Strategy Best Practices
Data Strategy Best Practices
 
Who Should Own Data Governance – IT or Business?
Who Should Own Data Governance – IT or Business?Who Should Own Data Governance – IT or Business?
Who Should Own Data Governance – IT or Business?
 
Data Management Best Practices
Data Management Best PracticesData Management Best Practices
Data Management Best Practices
 
MLOps – Applying DevOps to Competitive Advantage
MLOps – Applying DevOps to Competitive AdvantageMLOps – Applying DevOps to Competitive Advantage
MLOps – Applying DevOps to Competitive Advantage
 

Dernier

Dernier (20)

presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 

Smart Data Webinar: Deep QA (Question/Answer) - Lessons From Watson and Jeopardy!

  • 1. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. 7/17/2015 Deep QA (Question/Answer) Lessons From Watson and Jeopardy! October 13, 2016 Adrian Bowles, PhD Founder, STORM Insights, Inc. info@storminsights.com
  • 2. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Deep Question/Answering - Lessons from Watson & Jeopardy! The Game The Challenge Scope of the problem DeepQA Architecture & Processes Software, Hardware & Resources Next Steps
  • 3. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Answers must be given in the form of a question Last contestant to answer correctly chooses the next question Correct responses must satisfy the demands of both the clue and the category Jeopardy Six categories, 5 Questions for each category, $100-500 based on difficulty Double Jeopardy Six categories, 5 Questions for each category, $200-1,000 based on difficulty, and 3 hidden questions allow the person who chooses them to bet everything they have at that point in the game Final Jeopardy Player must have a positive balance from the previous round to play Players see the category and then decide - secretly - how much to wager The question is presented 30 seconds to answer Playing the Game: Wikipedia, The Free Encyclopedia. October 12, 2016, 02:40 UTC. Available at: https://en.wikipedia.org/w/index.php?title=Jeopardy!&oldid=743931483. Accessed October 12, 2016.
  • 4. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Open Domain, broad use of language - Jeopardy! questions often involve puns, ambiguity… IBM reviewed a sample of 20,000 questions, and found 2,500 distinct lexical answer types (LA No single LAT accounted for more than 3% of the total For each category, there could be thousands of questions Best players provide correct answers ~85% of the time Best players know what they don’t know - base their bets on their confidence ~3 seconds to answer questions Challenges of Jeopardy! for Machines: Players may only use the data/knowledge they have on arrival - no lifelines, resources… Constraint Winning Jeopardy! requires a contestant to answer ~70% of the questions, with 80%+ precision.
  • 5. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Predicting lexical answer types in open domain question and answering (qa) systems US 20130035931 A1 2013, Ferrucci, Gliozzo, Kalyanpur
  • 6. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Precisio n Speed Confide nce Quality SpeedCost Business Constraints Jeopardy! Constraints
  • 7. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Look for Similar Solved Problems Accept or Create Problem Statement Generate Hypotheses Identify Evidence in Corpus Score Evidence Score Hypotheses Present Results Get Feedback Train ModelOrientAct Observe Decide World Model Formalizing the Decision-Making Process Boyd’s Loop John Boyd (1927- 1997) Continuous Learning
  • 8. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Machine Learning NLU NLG Informatio n Retrieval Reasoning Knowledge Represent ation Evidence Gather Decide Evaluate Weigh Generate Hypothese s Automating QA
  • 9. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. * Building Watson: An Overview of the DeepQA Project, AI Magazine, Fall 2010 Issue, Ferrucci, Brown, Chu-Carroll, Fan, Gondek, Kalyanpur, Lally, Murdock, Nyberg, Prager, Schlaefer, Welty. Build a database of question/answer pairs Build a formal model of the world Build a search engine What they didn’t do: What they did: DeepQA - “a massively parallel probabalistic evidence-based architecture.”* Develop reusable NLU tech to analyze text Analyze sources - structured and unstructured - to capture background knowledge Apply knowledge representation and Reasoning (KRR) to the resulting structured knowledge Use machine learning to generate and score hypotheses
  • 10. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Massively Parallel Probabalistic Evidence-based Architecture
  • 11. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Content Acquisition Building the corpus For Jeopardy! this had to be completed before the game commenced. Ingested encyclopedias, dictionaries, thesauri, newswire articles, literary works, databases, taxonomies, ontologies… IRL, we can identify and use new resources based on the problem at hand.
  • 12. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Question Analysis What is being asked? Question classification: any words with double meanings? Puzzle question, factoid…? Detect focus LAT relations
  • 13. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Relation-detection “They’re the two states you could be reentering if you’re crossing Florida’s norther border.” Category: Head North borders(Florida, ?,x,north)
  • 14. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
  • 15. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
  • 16. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Hypothesis Generation & Scoring Use a candidate answer with the question, try to prove correct with a degree of confidence supported by the evidence. Scoring may use a variety of relationships: temporal spatial geospatial taxonomic classification correlation between candidate and question…
  • 17. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Evaluating Potential Answers Watson scores evidence in multiple dimensions What works for a factoid question may not work for a puzzle question. “Chile shares its longest land border with this country.”
  • 18. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
  • 19. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved.
  • 20. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Merging & Ranking Identifying the most likely answer based on confidence scores. Answer scores are merged before ranking and confidence estimation. Uses ML approach to compare with training set data when confidence scores in different categories result in “too close to call” results.
  • 21. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Wikipedia, The Free Encyclopedia. October 12, 2016, 17:06 UTC. Available at: https://en.wikipedia.org/w/index.php?title=Watson_(computer)&oldid=744021754. Accessed October 12, 2016.
  • 22. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Software Apache Hadoop http://hadoop.apache.org Apache UIMA - Unstructured Information Management Architecture http://uima.apache.org IBM DB2 Linux (Suse Enterprise Server 11)
  • 23. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Resources Wordnet(R) Princeton University "About WordNet." WordNet. Princeton University. 2010. <http://wordnet.princeton.edu> Wordnet(R)
  • 24. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Resources Wordnet(R) Princeton University "About WordNet." WordNet. Princeton University. 2010. <http://wordnet.princeton.edu> Wordnet(R)
  • 25. Copyright (c) 2016 by STORM Insights Inc. All Rights Reserved. 9/28/2011 IBM Power 750 90 servers, 32 cores/server, 2880 Cores in 10 racks 16Tb RAM ~80TeraFLOPS 80,000,000,000,000FLOPS Hardware
  • 26. Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. Next Steps…
  • 27. For more information: Copyright (c) 2016 by STORM Insights Inc. All Rights reserved. adrian@storminsights.com Twitter @ajbowles Skype ajbowles Upcoming Webinar Dates & Topics November 10 Emerging Hardware Choices for Modern AI Data Management December 8 Leverage the IOT to Build a Smart Data Ecosystem 2017 Webinar Themes Technology Trends Market Trends Communicating Learning Understanding Reasoning Planning