Your SlideShare is downloading. ×
0
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Wolfram alpha A Computational Knowledge Engine  Interesting Technology
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

Wolfram alpha A Computational Knowledge Engine Interesting Technology

909

Published on

Wolfram alpha A Computational Knowledge Engine Interesting Technology

Wolfram alpha A Computational Knowledge Engine Interesting Technology

Published in: Education, Technology
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
909
On Slideshare
0
From Embeds
0
Number of Embeds
5
Actions
Shares
0
Downloads
101
Comments
0
Likes
1
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  1. Submitted by: Manish Kumar (www.manishprajapati.in) Information Technology
  2. WolframAlpha Computational Knowledge Engine
  3. Contents :- Overview History Technology – The “Four Pillars” Technology – Interesting Facts Examples Conclusions
  4. Overview:  Users submit queries & requests . Wolfram Alpha then computes answers from a knowledge base of curated, structured data that come from other sites.  It generates output by doing computations from its own internal knowledge base instead of searching the web and returning link.  WolframAlpha thus differs from semantic search engines, which index a large number of answers and then try to match the question to one.  Using the Mathematica toolkit, Wolfram Alpha can respond to natural language questions and generate a human-readable answer.
  5. Overview:  Goal : “Wolfram|Alpha's long-term goal is to make all systematic knowledge immediately computable and accessible to everyone.”  Some of the explored areas:
  6. History  WolframAlpha was officially launched on May 18, 2009.  It is the culmination of 5 years of work, and 26 more years of previous development.  December 3, 2009, an iPhone app was introduced.  October 6, 2010 an Android version of the app was released.  It is now available for Kindle Fire and Nook.  Also 71 apps are available which use the Wolfram Alpha engine for specialized tasks.
  7. Curation Technology– the “Four Pillars” Formalization NLP Visualization
  8. 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.
  9. Pillar1 - Curation
  10. Pillar 2 - Formalization  Organizing the curated data so that it can be computable.  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.  Mathematica’s language is able to represent data of all kinds using arbitrarily structured symbolic expressions  Mathematica already includes a very big set of algorithms and functions, making it easier to implement new (usually more complex) algorithms
  11. Pillar 2 - Formalization
  12. 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 Natural language processing MatheMatica Algorithm Answer Factual Queries Database
  13. Pillar 3 – Natural Language Processing
  14. 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
  15. Pillar 4 – Visualization
  16. Pillar 4 – Visualization
  17. Facebook report
  18. Technology Interesting Facts  Wolfram Alpha is written in 15 million lines of Mathematica code.  Wolfram Alpha runs on more than 10,000 CPUs.  The database currently includes hundreds of datasets, such as "All Current and Historical Weather".  The curated datasets are checked for quality either by a scientist or other expert in a relevant field.  Its server technology is based on Apache Web servers accessing clusters of webMathematica servers.  On the Server side ,it’s using JSP.  On the client side, it's using AJAX(JavaScript).
  19. 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.

×