This <a href="statLettres.jar">software</a> reads text and generates new ones based on statistics.<br/>
I also have an older version of it written in processing, quicker but less subtle.<br/>
Here is also an <a href="massacre.xml">exemple xml</a> file with it.<br/>
<br/>
<img src="statLettres.PNG" /><br/>
<br/>
It was written in 2009.<br/>
It is now even more ridiculous compared to modern text-generation techniques.<br/>
It's based on n-grams but I'm not sure the technique can be called Markov chain.<br/>
As far as I know, most Markov chains take a given element into account to predict the next one, here the "chains" contain several elements to define what the next element should be.<br/>
While generating new text it will increment the length of the chains as much as possible but stop at some point to always make sure a given chain allows several possible alternative continuations.<br/>
<br/>
Back then I created various pieces of weird art with it, including this <a href="http://nurykabe.com/dump/video/les%20deux%20am%c3%a9riques/">nostalgic movie</a>.<br/>
<br/>
<br/>
<br/>