October 3, 2012 2:08 PM
Allison Sparrow shared a link to Patentula, a company interested in finding better ways to explore patent data and hunt patent trolls. What caught my attention is this quote from the video below:
What we tried to do with it, is bypass any sort of keyword processing in order to find similar patents. The reason we’ve done this is to avoid the problems encountered by other systems that rely on natural language processing or semantic analysis simply because patents are built to avoid detection by similar keywords…we use network topology (specifically citation network topology) to mine the US patent database in order to predict similar documents.
When dealing with a large text dataset, most folks jump right into NLP and semantic analysis, it’s interesting to learn when that’s not such a good idea.
Check out the full video:
… and if you wanted to see just how exciting troll hunting can be:
>8-]
Posted by maxdemarzi
Tags: graph database, network, network topology, patent, relationship graph
Mobile Site | Full Site
Get a free blog at WordPress.com Theme: WordPress Mobile Edition by Alex King.
[…] Hunting Trolls with Neo4j! by Max De Marzi. […]
By Hunting Trolls with Neo4j! « Another Word For It on October 3, 2012 at 7:19 PM