and Linguistics

Chinese word structure annotation is potential-ly useful for many NLP tasks, especially for Chinese word segmentation. Li and Zhou (2012) have presented an annotation for word structures in the Penn Chinese Treebank. But they only consider words that have productive affixes, which covers 35 % of word types in that corpus. In this paper, we propose a lin-guistically inspired annotation that covers var-ious morphological derivations of Chinese in a more general way, such that almost all multi-ple-character words can be structurally ana-lyzed. As manual annotation is expensive, we propose a semi-supervised approach to auto-matic annotation, which combines the maxi-mum entropy learning and the EM iteration for the Gaussian mixture model. The proposed method has achieved an accuracy of 90 % on the testing set.