A Letter Tagging Approach to Uyghur Tokenization

In this paper, we present a letter tagging approach(LTA) to Uyghur tokenization. Experiments show that the problem with label bias (rich and complex suffixes) problem to be resolved using LTA combined with CRFs, so it is more effective than previous work, the accuracy of word tokenization reaches 93.3%. In future our tokenization research will be very useful to other Altaic languages information processing.