2013 | OriginalPaper | Buchkapitel
Shallow Parsing of Chinese Based on HMM Model
verfasst von : Zheng Weifa, Xie Wenliang
Erschienen in: Intelligence Computation and Evolutionary Computation
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Complete parsing is difficult to meet the need of precision and recall rate in Chinese. To address this problem, a new model for shallow parsing of Chinese is presented in this paper. We adopt Church theory and carry on Chinese phrases recognition based on HMM; improve the precision rate of sentences separation by improving the observance probabilities of HMM model and making use of the context information of the Chinese sentences. At the same time, by studying the rules of Chinese sentence, we extract some rules useful for ambiguity elimination. The experimental result indicates that the model based on HMM has high precision and recall rate.