Hybrid Chinese Text Chunking

Abstract

Text chunking is an effective method to decrease the difficulty of natural language parsing. In this paper, a statistical method based on hidden Markov model (HMM) is used for Chinese text chunking. Moreover, a transformation based error-driven learning approach is adopted to improve the performance. The definition of transformation rule templates is the key problem of this machine learning approach. All the templates are learned from the corpus automatically in this paper. The precision using HMM is 88.19% and the precision is 92.67% combining HMM and transformation based error-driven learning