Currently we are regularly analyzing sets of paragraphs every month. I would like to automate this and split each paragraphs into chunks of data.
To do this I would like to employ a neural network. However, I am not really very familiar with creating neural networks.
Any ideas or starting point on how to do this using Neuroph or maybe in other framework/approaches?
Edit for more info as suggested.
I have very little experience on neural networks though I have some introduction with it in college. However I am very much familar with java
The data is around 3 megabytes only and consists of rules and relationships for a single domain. This means that the data is complex but relatively limited though still free-form English language.