Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Deepak Krishnan | Consultant - Data Scientist
❏ Expert on various Big Data and Machine Learning initiatives
❏ Experienced ...
Agenda
❏ Problem Statement
❏ Solution
❏ Summary
❏ Questions?
Problem Statement
User Experience
User Engagement
Search
Solutio
n
Solution
Solution
❏ Identify key operands & operators within natural language query
❏ Convert them into a series of connected expre...
Solution
[Revised]
Example:
Tokenizer
❏ Acts an FSA to access inverted index
❏ Emits annotations whenever a buffer matches an operator
❏ Ability to identify com...
Expression Parser
❏ Generated using parser generator
❏ Supports conjunction, disjunction, negation operators
❏ Responsible...
Expression Parser
Example: Show me Java or PHP openings
This will be reduced by
EXPR OR_OPERATOR EXPR
which has an RHS tha...
External Knowledge Bases
❏ Integrated into the expression parser for data intelligence
❏ The application uses NLP date par...
Summary
Search API
❏ Acts as natural language quering modules
❏ Acts as a RESTful API endpoint to which clients can connect to via...
Expression Parser
❏ Uses series of tokens to make transitions in a finite state machine
❏ Ingestion of the tokens into the...
MongoDB Expertise at QBurst
MongoDB Expertise at QBurst
❏ Consulting – Strategy & Planning
❏ Solutions Architecting
❏ Design & Implementation
❏ Big Da...
Questions?
Thank You
Email: info@qburst.com
www.qburst.com
USA | UK | Poland | UAE | India | Singapore | Australia
Running Natural Language Queries on MongoDB
Upcoming SlideShare
Loading in …5
×

Running Natural Language Queries on MongoDB

3,024 views

Published on

One of the most sought-after features of any user centric web application is the search functionality. QBurst revamped the search interface by using NLP and integrating with MongoDB. Their solution is designed to identify key components and operators within a natural language query and use it against MongoDB to extract records. This session explains QBurst's technical solution in detail.

Published in: Technology
  • Be the first to comment

Running Natural Language Queries on MongoDB

  1. 1. Deepak Krishnan | Consultant - Data Scientist ❏ Expert on various Big Data and Machine Learning initiatives ❏ Experienced in schema design for Big Data storage systems Praveen Rajasekhar | Director - Business Development ❏ <bio to be updated> ❏ <bio to be updated> Speakers
  2. 2. Agenda ❏ Problem Statement ❏ Solution ❏ Summary ❏ Questions?
  3. 3. Problem Statement
  4. 4. User Experience
  5. 5. User Engagement
  6. 6. Search
  7. 7. Solutio n
  8. 8. Solution
  9. 9. Solution ❏ Identify key operands & operators within natural language query ❏ Convert them into a series of connected expressions ❏ Dynamically build a query which runs against MongoDB instance ❏ Aggregate search results [Revised]
  10. 10. Solution
  11. 11. [Revised] Example: Tokenizer
  12. 12. ❏ Acts an FSA to access inverted index ❏ Emits annotations whenever a buffer matches an operator ❏ Ability to identify common data types such as date, time etc. ❏ Emits the matched expressions as a sequential stream of annotations [Revised] Tokenizer
  13. 13. Expression Parser ❏ Generated using parser generator ❏ Supports conjunction, disjunction, negation operators ❏ Responsible for taking in a stream of annotations and reducing it ❏ Creates the equivalent MongoDB query during reduction process [Revised]
  14. 14. Expression Parser Example: Show me Java or PHP openings This will be reduced by EXPR OR_OPERATOR EXPR which has an RHS that will convert this to an OR query in MongoDB
  15. 15. External Knowledge Bases ❏ Integrated into the expression parser for data intelligence ❏ The application uses NLP date parsers, ConceptNet (knowledge bases) ❏ Improved data intelligence [Revised]
  16. 16. Summary
  17. 17. Search API ❏ Acts as natural language quering modules ❏ Acts as a RESTful API endpoint to which clients can connect to via HTTP Tokenizer ❏ Passes the stream of tokens to an expression parser Summary [Revised]
  18. 18. Expression Parser ❏ Uses series of tokens to make transitions in a finite state machine ❏ Ingestion of the tokens into the expression parser is based on a sliding window model where the window size is dynamic Summary [Revised]
  19. 19. MongoDB Expertise at QBurst
  20. 20. MongoDB Expertise at QBurst ❏ Consulting – Strategy & Planning ❏ Solutions Architecting ❏ Design & Implementation ❏ Big Data Analytics & Integration ❏ Social Media Analytics & Solutions ❏ IoT Storage, Processing, and Prediction Solutions
  21. 21. Questions?
  22. 22. Thank You Email: info@qburst.com www.qburst.com USA | UK | Poland | UAE | India | Singapore | Australia

×