N-th Order Ergodic Multigram HMM for Modeling of Languages without Marked Word Boundaries

I,;rgodie IIMMs have been successfully used for modeling sentence production. llowever for some oriental languages such as Chinese, a word can consist of multiple characters without word boundary markers between adjacent words in a sentence. This makes wordsegmentation on the training and testing data necessary before ergodic ItMM can be applied as the langnage model. This paper introduces the N-th order Ergodic Mnltigram HMM for language modeling of such languages. Each state of the IIMM can generate a variable number of characters corresponding to one word. The model can be trained without wordsegmented and tagged corpus, and both segmentation and tagging are trained in one single model. Results on its applicw Lion on a Chinese corpus are reported.