A WORD SEGMENTATION ALGORITHM FOR CHINESE LANGUAGE BASED ON N-GRAM MODELS AND MACHINE LEARNING

梁南元,汉语计算机自动分词知识,中文信息学报,1989,4(2),29-33.[2]王德春,应用语言学概论,上海,上海外语教育出版社,1997年12月第1版,88-120.[3]E. Charniak, C. Hendrickson, N. Jacoboson, M. Perkowitz, Equations for part-of speech tagging,AAAI-93, 1993, 784 789.[4]K. Church, A stochastic parts program and noun phrase parser for unrestricted text, ANLP-88,1998, 136-143.[5]S. Sakai, Morphological category bigram: A single language model for both spoken language and text, ISSD-93, 1993, 97-90.[6]M. Yamamoto, A re-estimation method for stochastic language modeling from ambigous obser-vations, in Proceeding of WVLC-96, California, 1996, 155-167.[7]赵以宝, 孙圣和, 一种基于单字统计二元文法的自组词音字转换算法,电子学报, 1998, 26(10), 55-58.[8]F. Jelinek, Self-Organized Language Modeling for Speech Recognition, IBM Research Report,IBM T, J. Watson Research Center, 1985. Reprinted in Reading in Speech Recognition, Waibel,A., and Lee, K-F. (Eds.), Morgan Kaufann Publishers, 1990, 450-506.[9]S.M. Katz, Estimation of probailities from sparse data for the language model component ofspeech recognizer, IEEE Trans. on Acousttics, Speech, and Signal Processing, 1987, ASSP-35(3),400-401.[10]R. Rosenfeld, The CMU statistical language modeling toolkit and its use in the 1994 ARPA CSR evaluation, In the Proc. of ARPA Spoken Language Systems Technology Workshop, Washington, 1995, 47-50.