Abstract
Contrast to the traditional Chinese writing that writes characters consecutively without spaces in-between, LangGeh orthography proposes writing in (simple) extended words and simple short phrases. In comparison, English is written in words. The distinction between a traditional word and an extended word is that the latter includes, in addition to the traditional words in Mandarin, two character phrases and other words of easily recognizable patterns. This inclusion greatly simplifies the syntactic tagging of our corpus. With hand-tagged corpus, this thesis also gives a preliminary study of the automatic tagging of extended words and simple short phrases in LangGeh Mandarin text.