Top Banner
23
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Page 1: Running Natural Language Queries on MongoDB
Deen Edger
Content has been shortened. Original content included in Speaker notes. Please review
Page 2: Running Natural Language Queries on MongoDB

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

Page 3: Running Natural Language Queries on MongoDB

Agenda

❏ Problem Statement

❏ Solution

❏ Summary

❏ Questions?

Page 4: Running Natural Language Queries on MongoDB

Problem Statement

Page 5: Running Natural Language Queries on MongoDB

User Experience

Page 6: Running Natural Language Queries on MongoDB

User Engagement

Page 7: Running Natural Language Queries on MongoDB

Search

Page 8: Running Natural Language Queries on MongoDB

Solution

Page 9: Running Natural Language Queries on MongoDB

Solution

Mathen Abraham
Example query here
Mathen Abraham
Write example connected expressions here
Mathen Abraham
Write example query here
Page 10: Running Natural Language Queries on MongoDB

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]

Page 11: Running Natural Language Queries on MongoDB

Solution

Page 12: Running Natural Language Queries on MongoDB

[Revised]

Example:

Tokenizer

Page 13: Running Natural Language Queries on MongoDB

❏ 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

Deen Edger
Please review the content. Original from Deepak is included in the speaker notes
Page 14: Running Natural Language Queries on MongoDB

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]

Page 15: Running Natural Language Queries on MongoDB

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

Page 16: Running Natural Language Queries on MongoDB

External Knowledge Bases

❏ Integrated into the expression parser for data intelligence

❏ The application uses NLP date parsers, ConceptNet (knowledge

bases)

❏ Improved data intelligence

[Revised]

Deen Edger
Content has been shortened. Original content included in Speaker notes. Please review
Page 17: Running Natural Language Queries on MongoDB

Summary

Page 18: Running Natural Language Queries on MongoDB

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]

Deen Edger
Content Rephrased
Page 19: Running Natural Language Queries on MongoDB

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]

Deen Edger
Content rephrased
Page 20: Running Natural Language Queries on MongoDB

MongoDB Expertise at QBurst

Page 21: Running Natural Language Queries on MongoDB

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

Page 22: Running Natural Language Queries on MongoDB

Questions?

Page 23: Running Natural Language Queries on MongoDB

Thank You

Email: [email protected]

USA | UK | Poland | UAE | India | Singapore | Australia