An EMD Based Approach to Transliteration Unit Alignment between English and Chinese

Author

Yang, Muyun ; Liu, Shujie ; Wang, Lei ; Li, Sheng ; Li, Jufeng ; Zhao, Tiejun ; Qi, Haoliang

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China

fYear

2008

fDate

16-19 Dec. 2008

Firstpage

1

Lastpage

4

Abstract

Machine transliteration is to translate the proper nouns in the source language according to its pronunciation into the target language. Recent orthographical based approach has improved the performance of machine translation significantly. Focusing on the transliteration unit alignment that provides a fundamental parameter for the model, this paper adopts a semi-supervised EMD approach-applying discriminative model over the original EM results. The experiment results prove it is substantial to the improvement of the transliteration performance.

Keywords

expectation-maximisation algorithm; language translation; learning (artificial intelligence); natural language processing; EM plus discriminative training algorithm; machine transliteration; semisupervised EMD approach; source language; transliteration unit alignment; Computer science; Decoding; Distributed computing; Globalization; Humans; Information processing; Information retrieval; Natural language processing; Natural languages; Probability distribution;

fLanguage

English

Publisher

ieee

Conference_Titel

Chinese Spoken Language Processing, 2008. ISCSLP '08. 6th International Symposium on

Conference_Location

Kunming

Print_ISBN

978-1-4244-2942-4

Electronic_ISBN

978-1-4244-2943-1

Type

conf

DOI

10.1109/CHINSL.2008.ECP.81

Filename

4730335