NLP – Connecting to WordNet

moment of clarity?   or finally saw the trees?

Digital Explorer is my mainstay at work right now, very early on within the development (maybe August 2016) the smart data chap in the team introduced me to WordNet, we connect our trends and solutions within Digital Explorer to it to improve the search.

So it struck me today, I should add the individual words in my NLP development app to the WordNet.    WordNet is a thesaurus model, each word connected across the graph as they relate to each other.

The connection to WordNet is also very simple, but once connected I can transverse the transcripts in very different ways.  People, Person, Users, Team can all become considered as part of the same set of phrases; adding

including the following within my import code connects any matching word into the WordNet

MATCH (n:WN_Word {word:'" + ImportWord +"'})
MATCH (w:Word {name:'" + ImportWord +"'})
MERGE (w)-[:WN_LINK]->(n);


For example, connecting digital returns the following

graph (5).pngThe nodes with numbers are the WN_Synset nodes, which build the connections to the related words.

red herring?   or something to explore further?


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s