running natural language queries on mongodb

23

Upload: mongodb

Post on 25-Jul-2015

241 views

Category:

Technology


0 download

TRANSCRIPT

Deen Edger
Content has been shortened. Original content included in Speaker notes. Please review

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

Agenda

❏ Problem Statement

❏ Solution

❏ Summary

❏ Questions?

Problem Statement

User Experience

User Engagement

Search

Solution

Solution

Mathen Abraham
Example query here
Mathen Abraham
Write example connected expressions here
Mathen Abraham
Write example query here

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]

Solution

[Revised]

Example:

Tokenizer

❏ 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

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]

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

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

Summary

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

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

MongoDB Expertise at QBurst

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

Questions?

Thank You

Email: [email protected]

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