I don't really understand what this abstract is saying. Can someone explain it for me?

Are they trying to apply NLP techniques to software source code? To what end?

Sounds interesting. Anything that makes reading source code easier is to be welcomed, but I'd like to see the paper, some results, and a working tool before judging this particular 'idea'.

To me the abstract sounds as though they are trying to create a tool that automatically discovers the real organization of the code as compared to the way that it might be actually represented in the various files that make it up at the moment. I very often see code in the big application that I work on (>1M lines) that is placed in one source file where it clearly belongs in another and many modules where there is a very miscellaneous collection of functions that have no obvious relation to each other.

However the submission date is 2017-04-01, also known as All Fools Day.

So could Messrs Amir Saeidi, Jurriaan Hage, Ravi Khadka, and Slinger Jansen please join the conversation (and bring the paper with them)?

The journal is real and open access, I must apologize for not noticing that the PDF isn't linked yet

I realize the journal is real, I was just speculating that the paper might not be. Real journals have jokes too.

I did a search for the authors and they seem reputable. But of course reputable people make jokes too. :-)

I'm still interested.

Literate programming?