A few days ago I discovered this initiative that I found very interesting and fun: during the month on November you have to develop a program to generate a novel of around 50k words. This is the 7th edition of the event.<p>I started reading the dev-logs (GitHub issues) of the past editions and discovered some great novels both in term of technology involved and also content.<p>Some gems:<p>* MARYSUE (<a href="https://github.com/catseye/MARYSUE" rel="nofollow">https://github.com/catseye/MARYSUE</a>), which aims to create an interesting novel with a plot and everything else (and the related write-up "A story compiler" (<a href="https://git.catseye.tc/MARYSUE/blob/master/doc/Overview%20of%20a%20Story%20Compiler.md)" rel="nofollow">https://git.catseye.tc/MARYSUE/blob/master/doc/Overview%20of...</a>)<p>* LIFE OF THE AZAR (<a href="https://github.com/NaNoGenMo/2017/issues/39" rel="nofollow">https://github.com/NaNoGenMo/2017/issues/39</a>), an archive/enciclopedia of some sort of an imaginary city of a couple of thousands of citizens describing the people, their relationships, events that happens in the city and much more<p>* THE DESERT OF THE WEST (<a href="https://github.com/dariusk/NaNoGenMo-2015/issues/156" rel="nofollow">https://github.com/dariusk/NaNoGenMo-2015/issues/156</a>), a generated guide of imaginary worlds together with a map generation alghoritm with rivers and erosion (<a href="http://mewo2.com/notes/terrain/" rel="nofollow">http://mewo2.com/notes/terrain/</a>) and a generator for city names based on natural language theories (<a href="http://mewo2.com/notes/naming-language/" rel="nofollow">http://mewo2.com/notes/naming-language/</a>)<p>* MEOW (<a href="https://github.com/dariusk/NaNoGenMo-2014/issues/50" rel="nofollow">https://github.com/dariusk/NaNoGenMo-2014/issues/50</a>) meow meow meeeooow mew<p>Some projects are based on Neural Networks, some on Markov Chains, some on simulations, some on Tracery grammars (<a href="https://tracery.io/" rel="nofollow">https://tracery.io/</a>), some on Prolog, some on "plain" text processing and some on a mix of all of these. (I found an overview of the approaches for the 2016 edition here <a href="https://github.com/NaNoGenMo/2016/issues/154" rel="nofollow">https://github.com/NaNoGenMo/2016/issues/154</a>)<p>I find all of this very fascinating and might start my own adventure with text generation in the next days.