Improving Graph Based Entity Resolution using Data Mining and NLP

This is a joint meetup with the Houston Natural Language Processing meetup. If your company would like to host this event, send a note to lynn@globaldatageeks.org

Abstract

“Hey, here are those new data files to add. I ‘cleaned’ them myself so it should be easy. Right?”
Words like these strike fear into the heart of all developers but integrating ‘dirty’ unstructured, denormalized and text heavy datasets from multiple locations is becoming the de facto standard when building out data platforms.
In this talk we will look at how we can augment our graph’s attributes using techniques from data mining (e.g. string similarity/distance measures) and Natural Language Processing (e.g. keyword extraction, named entity recognition). We will then walkthrough an example using this methodology to demonstrate the improvements in the accuracy of the resulting matches.

About the Speaker

Dave Bechberger (https://www.linkedin.com/in/davebechberger/)is a Sr. Architect at Gene by Gene, a genetic genealogy and bioinformatics company, where he works extensively on developing their next-generation data architecture. Dave has spent his career engaging in full stack software development but specializes in building data architectures in complex data domains such as bioinformatics, oil and gas, supply chain management, etc. He uses his knowledge of graph and other big data technologies to build out highly performant and scalable systems. Dave has previously spoken at a variety of international technical conferences including NDC Oslo, NDC London, and Graph DayTexas.