Leveraging microservices for relationship-based text exploration

Architecture

  1. A relationship extraction component enables a user to ingest a new document into the system and runs all analysis steps required for going from raw documents to interesting links and connections.
  2. A relationship storage component takes the extracted relationships and stores them in a manner that can be efficiently and flexibly queried.
  3. A relationship visualization component enables a user to explore the corpus of documents ingested into the system.
Abstract text exploration architecture

Relationship extraction

Overview of the OpenIE process
Relationship extraction pipeline overview

Relationship storage

Relationship visualization

Visualization of SPARQL query editor and response graph

Conclusion

Overview of end-to-end text exploration pipeline

Resources

--

--

--

Senior software engineer at Microsoft. https://justamouse.com

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Using Uncertainty to Interpret your Model

How to be a better data scientist… by being an interior designer

Hypothesis Testing | All a beginner needs to know

AeroSim #1 | A Data Science Project & Game Worth Sharing

From Proof of Concept to Production with data science

Coming Out of 2020: A Data-Driven Approach

What is Data ?

Generating things with code

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Clemens Wolff

Clemens Wolff

Senior software engineer at Microsoft. https://justamouse.com

More from Medium

Spinning Apache Kafka® Microservices With Cadence Workflows

Monitoring Application KPIs Using Structured Logging with Elasticsearch & Kibana

OpenTelemetry on Google Cloud: Unraveling the mystery

3 Exciting New Features from K8ssandra for Cassandra 4.0