DocumentCode
3300998
Title
Negative expression translation in Japanese and Chinese machine translation
Author
Zhang, Hong ; Ren, Fuji
Author_Institution
Fac. of Eng., Univ. of Tokushima, Tokushima
fYear
2008
fDate
19-22 Oct. 2008
Firstpage
1
Lastpage
7
Abstract
Because there are many differences between Chinese and Japanese about the nature, history, culture, life, manners and customs, it is natural that there are particular words in each language. It is necessary that these particular words meaning are mastered right and translated accurately in translation. Because of the complex corresponding relationship with Chinese in Chinese-Japanese machine translation, it is easy to occur a vagueness, due to the negative in the sentence, many mistranslations are caused by the commercial translation software. In this paper, we analyzed the negative expressionways in Chinese and Japanese languages to translate Chinese negative sentences by using the selection rules of Chinese negative words and position rules. If we translate the basic Japanese negative expression naide1 into Chinese, its meaning is mei2, bie. Translate nakute into Chinese, according to its negative meaning and grammatical rule, it may be translated into bu. In the current research, we investigated a rough use rules which abstracted from each typical examples including naide and nakute.
Keywords
language translation; natural language processing; Chinese machine translation; Chinese negative sentence translation; Japanese machine translation; Japanese negative expression translation; bu; commercial translation software; mei2; naide1 translation; nakute; selection rules; Automatic testing; Data mining; Entropy; Labeling; Natural languages; Power engineering and energy; Power system modeling; Support vector machines; System performance; Tagging; Japanese and Chinese; Machine Translation; Negative expression;
fLanguage
English
Publisher
ieee
Conference_Titel
Natural Language Processing and Knowledge Engineering, 2008. NLP-KE '08. International Conference on
Conference_Location
Beijing
Print_ISBN
978-1-4244-4515-8
Electronic_ISBN
978-1-4244-2780-2
Type
conf
DOI
10.1109/NLPKE.2008.4906788
Filename
4906788
Link To Document