A hybrid approach to Chinese-English machine translation

Author

Ying, Liu ; Qun, Liu ; Xiang, Zhang ; Baobao, Chang

Author_Institution

Inst. of Comput. Technol., Acad. Sinica, Beijing, China

Volume

2

fYear

1997

fDate

28-31 Oct 1997

Firstpage

1146

Abstract

A hybrid method for Chinese-English machine translation is presented. A rule-based analysis is combined with statistical data. The rule-based lexical analyzer and syntactic analyzer leave some amount of ambiguity that is resolved using a statistical approach. A hidden Markov model (HMM) is used to return a score for each part of speech. An improved probabilistic context free grammar (PCFG) is used for syntactic scoring, and a probabilistic score function is used for the semantic aspect. In addition, parameters are usually estimated poorly when the training data is sparse. Smoothing the parameters is thus important in the estimation process. A back-off procedure is used to smooth the parameters

Keywords

computational linguistics; context-free grammars; hidden Markov models; knowledge based systems; language translation; natural languages; parameter estimation; probability; statistical analysis; Chinese-English machine translation; hidden Markov model; hybrid approach; parameter estimation; parameter smoothing; probabilistic context free grammar; probabilistic score function; rule-based analysis; rule-based lexical analyzer; statistical approach; statistical data; syntactic analyzer; syntactic scoring; training data; Artificial intelligence; Computers; Context modeling; Hidden Markov models; Intelligent structures; Natural language processing; Parameter estimation; Smoothing methods; Speech; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Processing Systems, 1997. ICIPS '97. 1997 IEEE International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-4253-4

Type

conf

DOI

10.1109/ICIPS.1997.669166

Filename

669166