A Morpheme-based Part-of-speech Tagger for Chinese
Guohong Fu, Jonathan James Webster · International Joint Conference on Natural Language Processing · 2008
This paper presents a morpheme-based part-of-speech tagger for Chinese. It consists of two main components, namely a morpheme segmenter to segment each word in a sentence into a sequence of morphemes, based on forward maximum matching, and a lexical tagger to label each morpheme with a proper tag indicating its position pattern in forming a word of a specific class, based on lexicalized hidden Markov models. This system have participated four closed tracks for POS tagging at the Fourth International Chinese Language Processing Bakeoff sponsored by the ACLSIGHAN.