Learning different linguistically-inspired patterns using subregular languages and transducers
A better description will be added very soon! :)
Sources of the real linguistic data:
- German data (
german.txt): https://github.com/enz/german-wordlist - Finnish data (
finnish.txt): https://github.com/douglasbuzatto/WordLists - Turkish data (
turkish.txt): http://www.swarthmore.edu/SocSci/harmony/public_html/dummyresults.html