Lexicon & associated files
Code to convert TnT lexicon file found on the Russian tagset and Russian statistical taggers webpage can be obtained here (.tgz)
The actual lexicon used to generate errors can be found here ... Thanks to Serge Sharoff for letting us make this available!
Some of the description of the changes and the motivations can be found in this paper (Dickinson, COLING-2010)
A file of errors generated in context, based on the TnT-tagged sample file at the Russian tagset and Russian statistical taggers webpage can be found here (version 1)
See this paper (Dickinson, COLING-2010) for more details
Analyzer & associated files ...