SlideShare a Scribd company logo
1 of 36
Wolfram Alpha
An introduction to the underlying
technology




            Pedro Gaspar
               SIGC
               2010/2011
Outline

 Introduction
 History
 Technology     – The “Four Pillars”
 Technology     – Interesting Facts
 Conclusions
 Reference



                         Wolfram Alpha - Pedro Gaspar   2
Introduction
 Real-time computational answering system
 Not a Search Engine like Google
 Not as static as Wikipedia or as an
  Encyclopedia




                        Wolfram Alpha - Pedro Gaspar   3
Introduction
   Goal:
    “Wolfram|Alpha's long-term goal is to make all systematic
    knowledge immediately computable and accessible to
    everyone.”
   Systematic knowledge:
    ◦   Objective Data
    ◦   Models
    ◦   Methods
    ◦   Algorithms
    ◦   Formulae

                                      Wolfram Alpha - Pedro Gaspar   4
Introduction
   Some of the explored areas:

Mathematics                Units & Measures Money & Finance
Statistics & Data Analysis Dates & Times       Socioeconomic Data
Physics                    Weather             Health & Medicine
Chemistry                  Places & Geography Food & Nutrition
Materials                  People & History    Education
Engineering                Culture & Media     Organizations
Astronomy                  Music               Transportation
Earth Sciences             Words & Linguistics Technological World
Life Sciences              Sports & Games      Web & Computer Systems
Computational Sciences Colors




                                       Wolfram Alpha - Pedro Gaspar   5
HISTORY
How did the project start?




                             Wolfram Alpha - Pedro Gaspar   6
History – Wolfram Alpha

 Project lead by Stephen
  Wolfram
 It is the culmination of 5
  years of work, and 25
  more years of previous
  development
 Stephen started Wolfram
  Research in 1987,
  focusing mainly on the
  Mathematica software



                               Wolfram Alpha - Pedro Gaspar   7
History – Wolfram Alpha

 In 2002 Stephen publishes “A New Kind of
  Science”
 In 2004 the company tries to apply the
  concepts from the book to a real-world
  product and thus started developing
  Wolfram Alpha
 In May 18th, 2009 Wolfram Alpha is officially
  launched to the public


                           Wolfram Alpha - Pedro Gaspar   8
History – Computable
Knowledge
 The history of Systematic Data and the
  Development of Computable Knowledge
  goes back to the 20,000 BC with the
  invention of arithmetic
 Scientific Books, Encyclopedias, Census,
  Maps and other sources of information
  have been collecting data since Ancient
  Mesopotamia




                         Wolfram Alpha - Pedro Gaspar   9
TECHNOLOGY
How does it work?




                    Wolfram Alpha - Pedro Gaspar   10
Technology – the “Four
Pillars”



                                               Visualizatio
Curation   Formalization   NLP                      n




                           Wolfram Alpha - Pedro Gaspar       11
Pillar1 - Curation
   Field Experts help the team find the best content
    sources and validate the data

   Community input is also accepted, but all the data
    has to go through a rigorous validation process
    before being used

   Almost none of their data comes from the Internet
    now

   It turned out that curation and data gathering was
    only 5% of the work
                                 Wolfram Alpha - Pedro Gaspar   12
Pillar1 - Curation




                     Wolfram Alpha - Pedro Gaspar   13
Pillar 2 - Formalization
   Organizing the curated data so that it can be
    computable

   Figuring out its conventions, units, definitions and
    how it connects to other data

   All these are encoded algorithmically in Wolfram
    Alpha so that they’re available when needed

   All the algorithms, models and equations are
    encoded into functions in Mathematica, the
    programming language behind Wolfram Alpha

                                  Wolfram Alpha - Pedro Gaspar   14
Pillar 2 - Formalization
   Mathematica’s language is able to represent data
    of all kinds using arbitrarily structured symbolic
    expressions

   As a result, the code is much more compact than in
    a lower-level language like Java or Python

   Mathematica already includes a very big set of
    algorithms and functions, making it easier to
    implement new (usually more complex) algorithms



                                 Wolfram Alpha - Pedro Gaspar   15
Pillar 2 - Formalization
   This creates a recursive process, that makes
    implementing new algorithms easier and easier
    through software reutilization




                               Wolfram Alpha - Pedro Gaspar   16
Pillar 2 - Formalization




                     Wolfram Alpha - Pedro Gaspar   17
Pillar 2 - Formalization




                     Wolfram Alpha - Pedro Gaspar   18
Pillar 3 – Natural Language
Processing
   How could users interact with the system and use
    its computing powers? Through human language is
    the most natural response

   The problem is not the one we are used to –
    instead of trying to make sense of a big set of
    words, the system has to map small pieces of
    human input (queries) into its large set of symbolic
    representations

   The implemented solutions generally achieve good
    results
                                 Wolfram Alpha - Pedro Gaspar   19
Pillar 3 – Natural Language
Processing




                    Wolfram Alpha - Pedro Gaspar   20
Pillar 3 – Natural Language
Processing




                    Wolfram Alpha - Pedro Gaspar   21
Pillar 3 – Natural Language
Processing




                    Wolfram Alpha - Pedro Gaspar   22
Pillar 3 – Natural Language
Processing




                    Wolfram Alpha - Pedro Gaspar   23
Pillar 4 – Visualization
   Wolfram Alpha’s ability to present results in formats
    other than text is one of its most visually appealing
    features

   Mathematica includes some functionality to deal
    with this challenge, through what they call
    “computational aesthetics”

   This automates, for a specific symbolic
    representation, what to present and how to present
    it


                                  Wolfram Alpha - Pedro Gaspar   24
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   25
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   26
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   27
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   28
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   29
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   30
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   31
Pillar 4 – Visualization




                      Wolfram Alpha - Pedro Gaspar   32
Technology – Interesting
Facts
   More than 10 trillion of data
   More than 50,000 types of algorithms and
    models
   Linguistic capacity for more than 1000
    domains
   More than 8 million lines of symbolic
    Mathematica code
   Runs in clusters of supercomputers,
    including the 44th largest supercomputer in
    the world - R Smarr
   Hundreds of terabytes of storage
                             Wolfram Alpha - Pedro Gaspar   33
Conclusions
 It is all a matter of representing data and
  mapping queries to the set of things they
  can compute about
 Uses an internal and pre-structured
  database to find the answers to the queries
 Computation brings a lot of value when
  comparing it to search engines like Google
 Little to no information available about how
  the system works internally


                           Wolfram Alpha - Pedro Gaspar   34
References
   Wolfram Alpha's website
   Wolfram Alpha's blog
   The Story of the Making of Wolfram Alpha
   Opinion: Wolfram Alpha: How does it work?
   How the hell does Wolfram Alpha Work
   Wolfram Alpha Architecture
   Wolfram Data Summit 2010
   Wolfram Alpha's YouTube channel
   What is Mathematica?

                           Wolfram Alpha - Pedro Gaspar   35
QUESTIONS?



 Pedro Gaspar
pgaspar@student.dei.uc.pt




                  Wolfram Alpha - Pedro Gaspar   36

More Related Content

Similar to Wolphram Alpha

Big Data Analytics-Open Source Toolkits
Big Data Analytics-Open Source ToolkitsBig Data Analytics-Open Source Toolkits
Big Data Analytics-Open Source Toolkits
DataWorks Summit
 

Similar to Wolphram Alpha (13)

WALFRAM ALPHA
WALFRAM ALPHAWALFRAM ALPHA
WALFRAM ALPHA
 
WOLFRAM MATHEMATICA PRESENTATION.pptx
WOLFRAM MATHEMATICA PRESENTATION.pptxWOLFRAM MATHEMATICA PRESENTATION.pptx
WOLFRAM MATHEMATICA PRESENTATION.pptx
 
Machine Learning with Spark
Machine Learning with SparkMachine Learning with Spark
Machine Learning with Spark
 
LD4KD 2015 - Demos and tools
LD4KD 2015 - Demos and toolsLD4KD 2015 - Demos and tools
LD4KD 2015 - Demos and tools
 
Wolfram ppt
Wolfram pptWolfram ppt
Wolfram ppt
 
Machine learning 2019
Machine learning 2019Machine learning 2019
Machine learning 2019
 
Getting Started with SPARK
Getting Started with SPARKGetting Started with SPARK
Getting Started with SPARK
 
WolframAlpha
WolframAlphaWolframAlpha
WolframAlpha
 
Teaching calculus with Wolfram Alpha
Teaching calculus with Wolfram AlphaTeaching calculus with Wolfram Alpha
Teaching calculus with Wolfram Alpha
 
Using Mahout and a Search Engine for Recommendation
Using Mahout and a Search Engine for RecommendationUsing Mahout and a Search Engine for Recommendation
Using Mahout and a Search Engine for Recommendation
 
Eecs441 company presentation
Eecs441 company presentationEecs441 company presentation
Eecs441 company presentation
 
Big Data Analytics-Open Source Toolkits
Big Data Analytics-Open Source ToolkitsBig Data Analytics-Open Source Toolkits
Big Data Analytics-Open Source Toolkits
 
Advanced MLflow: Multi-Step Workflows, Hyperparameter Tuning and Integrating ...
Advanced MLflow: Multi-Step Workflows, Hyperparameter Tuning and Integrating ...Advanced MLflow: Multi-Step Workflows, Hyperparameter Tuning and Integrating ...
Advanced MLflow: Multi-Step Workflows, Hyperparameter Tuning and Integrating ...
 

Recently uploaded

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 

Recently uploaded (20)

DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
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
 
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
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
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?
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 

Wolphram Alpha

  • 1. Wolfram Alpha An introduction to the underlying technology Pedro Gaspar SIGC 2010/2011
  • 2. Outline  Introduction  History  Technology – The “Four Pillars”  Technology – Interesting Facts  Conclusions  Reference Wolfram Alpha - Pedro Gaspar 2
  • 3. Introduction  Real-time computational answering system  Not a Search Engine like Google  Not as static as Wikipedia or as an Encyclopedia Wolfram Alpha - Pedro Gaspar 3
  • 4. Introduction  Goal: “Wolfram|Alpha's long-term goal is to make all systematic knowledge immediately computable and accessible to everyone.”  Systematic knowledge: ◦ Objective Data ◦ Models ◦ Methods ◦ Algorithms ◦ Formulae Wolfram Alpha - Pedro Gaspar 4
  • 5. Introduction  Some of the explored areas: Mathematics Units & Measures Money & Finance Statistics & Data Analysis Dates & Times Socioeconomic Data Physics Weather Health & Medicine Chemistry Places & Geography Food & Nutrition Materials People & History Education Engineering Culture & Media Organizations Astronomy Music Transportation Earth Sciences Words & Linguistics Technological World Life Sciences Sports & Games Web & Computer Systems Computational Sciences Colors Wolfram Alpha - Pedro Gaspar 5
  • 6. HISTORY How did the project start? Wolfram Alpha - Pedro Gaspar 6
  • 7. History – Wolfram Alpha  Project lead by Stephen Wolfram  It is the culmination of 5 years of work, and 25 more years of previous development  Stephen started Wolfram Research in 1987, focusing mainly on the Mathematica software Wolfram Alpha - Pedro Gaspar 7
  • 8. History – Wolfram Alpha  In 2002 Stephen publishes “A New Kind of Science”  In 2004 the company tries to apply the concepts from the book to a real-world product and thus started developing Wolfram Alpha  In May 18th, 2009 Wolfram Alpha is officially launched to the public Wolfram Alpha - Pedro Gaspar 8
  • 9. History – Computable Knowledge  The history of Systematic Data and the Development of Computable Knowledge goes back to the 20,000 BC with the invention of arithmetic  Scientific Books, Encyclopedias, Census, Maps and other sources of information have been collecting data since Ancient Mesopotamia Wolfram Alpha - Pedro Gaspar 9
  • 10. TECHNOLOGY How does it work? Wolfram Alpha - Pedro Gaspar 10
  • 11. Technology – the “Four Pillars” Visualizatio Curation Formalization NLP n Wolfram Alpha - Pedro Gaspar 11
  • 12. Pillar1 - Curation  Field Experts help the team find the best content sources and validate the data  Community input is also accepted, but all the data has to go through a rigorous validation process before being used  Almost none of their data comes from the Internet now  It turned out that curation and data gathering was only 5% of the work Wolfram Alpha - Pedro Gaspar 12
  • 13. Pillar1 - Curation Wolfram Alpha - Pedro Gaspar 13
  • 14. Pillar 2 - Formalization  Organizing the curated data so that it can be computable  Figuring out its conventions, units, definitions and how it connects to other data  All these are encoded algorithmically in Wolfram Alpha so that they’re available when needed  All the algorithms, models and equations are encoded into functions in Mathematica, the programming language behind Wolfram Alpha Wolfram Alpha - Pedro Gaspar 14
  • 15. Pillar 2 - Formalization  Mathematica’s language is able to represent data of all kinds using arbitrarily structured symbolic expressions  As a result, the code is much more compact than in a lower-level language like Java or Python  Mathematica already includes a very big set of algorithms and functions, making it easier to implement new (usually more complex) algorithms Wolfram Alpha - Pedro Gaspar 15
  • 16. Pillar 2 - Formalization  This creates a recursive process, that makes implementing new algorithms easier and easier through software reutilization Wolfram Alpha - Pedro Gaspar 16
  • 17. Pillar 2 - Formalization Wolfram Alpha - Pedro Gaspar 17
  • 18. Pillar 2 - Formalization Wolfram Alpha - Pedro Gaspar 18
  • 19. Pillar 3 – Natural Language Processing  How could users interact with the system and use its computing powers? Through human language is the most natural response  The problem is not the one we are used to – instead of trying to make sense of a big set of words, the system has to map small pieces of human input (queries) into its large set of symbolic representations  The implemented solutions generally achieve good results Wolfram Alpha - Pedro Gaspar 19
  • 20. Pillar 3 – Natural Language Processing Wolfram Alpha - Pedro Gaspar 20
  • 21. Pillar 3 – Natural Language Processing Wolfram Alpha - Pedro Gaspar 21
  • 22. Pillar 3 – Natural Language Processing Wolfram Alpha - Pedro Gaspar 22
  • 23. Pillar 3 – Natural Language Processing Wolfram Alpha - Pedro Gaspar 23
  • 24. Pillar 4 – Visualization  Wolfram Alpha’s ability to present results in formats other than text is one of its most visually appealing features  Mathematica includes some functionality to deal with this challenge, through what they call “computational aesthetics”  This automates, for a specific symbolic representation, what to present and how to present it Wolfram Alpha - Pedro Gaspar 24
  • 25. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 25
  • 26. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 26
  • 27. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 27
  • 28. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 28
  • 29. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 29
  • 30. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 30
  • 31. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 31
  • 32. Pillar 4 – Visualization Wolfram Alpha - Pedro Gaspar 32
  • 33. Technology – Interesting Facts  More than 10 trillion of data  More than 50,000 types of algorithms and models  Linguistic capacity for more than 1000 domains  More than 8 million lines of symbolic Mathematica code  Runs in clusters of supercomputers, including the 44th largest supercomputer in the world - R Smarr  Hundreds of terabytes of storage Wolfram Alpha - Pedro Gaspar 33
  • 34. Conclusions  It is all a matter of representing data and mapping queries to the set of things they can compute about  Uses an internal and pre-structured database to find the answers to the queries  Computation brings a lot of value when comparing it to search engines like Google  Little to no information available about how the system works internally Wolfram Alpha - Pedro Gaspar 34
  • 35. References  Wolfram Alpha's website  Wolfram Alpha's blog  The Story of the Making of Wolfram Alpha  Opinion: Wolfram Alpha: How does it work?  How the hell does Wolfram Alpha Work  Wolfram Alpha Architecture  Wolfram Data Summit 2010  Wolfram Alpha's YouTube channel  What is Mathematica? Wolfram Alpha - Pedro Gaspar 35
  • 36. QUESTIONS? Pedro Gaspar pgaspar@student.dei.uc.pt Wolfram Alpha - Pedro Gaspar 36

Editor's Notes

  1. Asfunções/algoritmosusadossãosempreosmaiseficientesparadiminuir a carga de processamento.
  2. Not limited to its set of data types
  3. ProdutoInternoBruto
  4. ProdutoInternoBruto
  5. ProdutoInternoBruto