Graph NLU: Natural Language Understanding with Python and Neo4j

In this session Dan Kondratyuk will talk about Graph NLU (https://github.com/Hyperparticle/graph-nlu) - a natural language understanding tool he built that leverages the power of graph databases.

https://www.youtube.com/watch?v=mTCqQ2e08Q8

Talk
Graph NLU is a research project that explores methods for storing high-level concepts dynamically.

I will talk about how I processed natural language facts and stored them in Neo4j to answer natural language questions about those facts.

I used the Facebook bAbI Tasks corpus for training and evaluating the system, and to process the text I used Python, NLTK, and Pandas inside an iPython notebook.

We'll be taking questions live during the session but if you have any before hand be sure to post them in the #neo4j-online-meetup channel of the Neo4j users slack (http://www.neo4j.com/slack).

We'll be hosting this session on YouTube live.

Time
09:00 PDT (UTC - 7 hours)
12:00 EDT (UTC - 4 hours)
16:00 UTC
17:00 BST (UTC + 1 hour)
18:00 CEST (UTC + 2 hour)

The Speaker
Dan Kondratyuk, Full Stack Developer at Boise State University

Dan is a member of the Speech, Language & Interactive Machines (SLIM) research group at Boise State University.

Having graduated with a Bachelor's in Computer Science, Dan is now pursuing a Master's in Computational Linguistics at European Universities, specializing in machine learning and natural language processing.