论文类型：期刊论文
发表刊物：ICIC Express Letters
收录刊物：Scopus、EI
卷号：3
期号：2
页面范围：177-182
ISSN号：1881803X
摘要：In order to solve problems of the Chinese word segmentation and POS tagging which are still existing in Chinese lexical analysis, a Hidden semi-CRF model, which has two chains of states with unequal number of states, is proposed for the Chinese lexical analysis. The Hidden semi-CRF detects the words together with their part-of-speech regardless whether the words are in the system dictionary or not. A new-words-generating framework is also built for training and testing, under which the definition and distribution of the new words conforms to the characteristic of the ones in real text. The proposed framework enhances the performance ofnew words detecting and POS tagging, so that the overall precision of the system for Chinese lexical analysis could be further increased. The experiment results show that the proposed method is capable of detecting even low frequency new words, which in return increases the overall precision of Chinese word segmentation and POS tagging in Chinese lexical analysis. ? 2009 ISSN.