Automatic Morphological Tagging of Contemporary Uighur Corpus

Abstract

In this paper, we propose methods of Uighur word lemmatization by using of morphemic analysis and word's structural analysis, integrating morphological processing and part-of speech (POS) tagging, so as to find linguistic information and automatic POS of Uighur Corpus as the final purpose. For the regular words, the accuracy of word lemmatization reach 85% and POS reach 80%