Maybe there are some in comp.lang.perl.misc on Usenet:
https://groups.google.com/d/msg/comp.lang.perl.misc/3LxcmlHkcts/WLms2U7GCQAJYesterday we made the ghost101.pl AI able to recognize the stems of bootstrap Russian verbs by means of the $prc "provisional recognition" variable. We had to enhance the verbs in the bootstrap by making sure that there was a concept-number not only at the end of the word, but also next to each auditory engram from the final character of the verb-stem up through the end of the word. Today we need to make sure that new Russian verbs get stored by the Perl AI
http://ai.neocities.org/P6AI_FAQ.html in the same format -- with concept-numbers stored from the end of the stem to the end of the verb. Let us get to work and then come back and report our success or failure.
http://www.sourcecodeonline.com/details/ghost_perl_webserver_strong_ai.html