Natural Language Processing with Neo4j
Recent natural language processing advancements have propelled search engine and information retrieval innovations into the public spotlight. People want to be able to interact with their devices in a natural way. In this talk I will be introducing you to natural language search using a Neo4j graph database. I will show you how to interact with an abstract graph data structure using natural language and how this approach is key to future innovations in the way we interact with our devices.
Published on: Mar 3, 2016
Transcripts - Natural Language Processing with Neo4j
Processing with Neo4j
This is a hobby of mine
I’m passionate about it
It’s always a work in progress
I do it for fun
Machine Learning Focuses
Natural Language Processing
Commitment to unsupervised
Why NLP and Graphs?
I wanted a better way to learn with less
I wanted something a little more
I’m mostly self-taught, so I wanted
something that made self-learning
easier for others.
Importance of NLP
I’m inspired by the idea of
machines learning from
NLP is important for finding
valuable information in noisy
I’m a Developer Evangelist for
Neo4j, so I’m kind of a fan of
Algorithms can learn
As long as it can store information and retrieve it in enough
time for it to be of any use.
Learning requires storage
To learn, storage is required.
For NLP, storage is sometimes a
second class citizen.
Much focus is on the algorithm first,
then storage second.
But really, it’s storage and retrieval
of big data that is the problem.
Machine learning isn’t magic or hard to understand. It’s real stuff.
We know how to do it.
It’s easily articulated.
ML algorithms solve big computational problems today.
It’s based on the idea of machines learning from prior experiences
Formulate a Hypothesis
When you analyze data, the
outcome is usually a hypothesis.
An hypothesis is a conclusion based
on limited data.
There are always more pieces
needed to solve the puzzle.
Build on Past Experience
By experience, I mean DATA.
Machine Learning techniques are
entirely based on collection and
analysis of recorded data.
So storage is really important if you
want to do machine learning
You cannot play baseball without
your brain. Don’t try it.
The Problem with AI
The problem with AI is that it seems like
Some people say strong AI is possible.
There are some people that deny that it is
It is a central theme in many fictional
fantasy films and book genres.
It’s in Greek mythology.
Is AI Misunderstood?
Researchers admit to not fully
understanding how intelligence
works in the human brain.
We generally understand how it
works, but no consensus on how to
recreate it in machines.
AI is really just the act of perceiving
an environment and maximizing
chances of success.
You get the point.
Now why is a Graph Database useful for unsupervised
Let’s consider the problem I stated earlier.
I wanted to build a better way to summarize and
learn from Wikipedia’s combined knowledge.
Unsupervised Learning on
How do you learn about
I started by observing myself learning from reading
I searched for an interesting term on Google.
I read through the article’s text word by word.
The Learning Algorithm
As I read the article’s text, I would sometimes come
across a phrase or term I had not seen before.
Before continuing reading I would open up a new tab
and search for the unrecognized phrase.
It was a well defined recursive algorithm.
I would drill down n-times on unrecognized article
terms until returning to the original article text.
A Self-Learning Algorithm
In the computer’s world, this process
would result in an ontology of labeled
Which looks a lot like a graph.
But how would I store the results?
If only there were a database for that..
Neo4j is a graph database
…and graphs are everywhere!
Simple Clustering Model
Summarizing Article Text
What about the NLP stuff?
This is how I did it.
The seed article
You start with a seed article which is the first article text
to start the learning algorithm with.
Fetch text from Wikipedia
Get the unstructured text and meta data from
Sliding text window
I formulated dynamic RegEx templates and treated
them as a hypothesis.
The RegEx template would slide word by word through
the text, searching for unrecognized phrases
(n known word matches + 1 wildcard word match)
Looking for redundant phrases
As each unrecognized phrase is encountered, the
dynamic RegEx is then matched against the entire
The algorithm looks for more than 2 identical phrases
within the article’s text.
It appends a 3rd wildcard word match to the template
and then rescans the text for redundant phrases until
none are found.
Identify Redundancy of Text
This recursive matching process within the local article’s
text resulted in finding the duplicate phrases of a
“The King of Sweden” has 2 appearances in an article,
so that must be important to the topic of Sweden.
Better go search for an article stub on “The King of
Graph Storage and Retrieval
Every time a phrase that doesn’t exist as a node in
Neo4j is encountered, it becomes a target of
investigation, kind of like a hypothesis.
Each sentence that contains the extracted phrase is also
added to Neo4j as a content node.
Relationships are added between nodes, showing
Phrases can be found within other phrases, denoting a
grammatical inheritance hierarchy mapped to a variety
of content nodes and articles.
Phrase Inheritance Graph Data
“X Y Z.”
“X Y Z”
Graphs are everywhere.
Thanks for coming to my talk!
Please look me up on Twitter and LinkedIn!