Title :
Experiments for various alignment models in Chinese-to-English SMT
Author :
Zhou, Yu ; Zong, Chengqing ; Xu, Bo
Author_Institution :
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
fDate :
30 Oct.-1 Nov. 2005
Abstract :
In this paper we analyze and compare three basic word alignment models to acquire the useful knowledge and parameters for the statistical machine translation. A series of experiments are made and a very detailed analysis based on the experiments is given. According to the different features of the three models, the merits and demerits of the models are described and analyzed respectively. Finally, the word alignment probabilities and the phrases extracted using HMM Viterbi-alignment are used to develop the Chinese-to-English statistical machine translation system. The experimental results show that the translation quality will be increased with the preprocessing of the training data, joining of the dictionary and enlarging the translation grain appropriately.
Keywords :
grammars; hidden Markov models; language translation; maximum likelihood estimation; natural languages; Chinese-to-English SMT; HMM Viterbi-alignment; statistical machine translation; word alignment model; Automation; Data mining; Entropy; Laboratories; Natural languages; Pattern analysis; Pattern recognition; Probability; Surface-mount technology; Training data; experiment analysis; statistical machine translation; word alignment;
Conference_Titel :
Natural Language Processing and Knowledge Engineering, 2005. IEEE NLP-KE '05. Proceedings of 2005 IEEE International Conference on
Print_ISBN :
0-7803-9361-9
DOI :
10.1109/NLPKE.2005.1598778