Based on our experiments, we found that segmenting and not segmenting a word have their own advantages and disadvantages. When translating the language pairs in which the words are not segmented by spaces, WS should be taken into consideration. Therefore, the word segmentation (WS) problem often is addressed first in natural language processing in general and in machine translation (MT) from Chinese or Vietnamese into other languages in particular and vice versa. In Vietnamese, spelling words are separated by one space, and the punctuation is located immediately after the spelling words.
#Chinese vietnamese english translator and dictionary series#
A Chinese sentence includes a series of characters, including punctuation, and they are located next to each other without any spaces.
Unlike Western languages, typically English, the words in Chinese and Vietnamese are not distinguished by spaces. The experimental results showed that our method improved the performance of machine translation over that of character or word level translation. And at the character level, a statistical translation is used. In addition, a hybrid approach that combines statistics and rules is used to translate on the word level. In this paper, we propose a new method for translating Chinese to Vietnamese based on a combination of the advantages of character level and word level translation. Therefore, while translating, whether it should be segmented or not becomes more important. Since Chinese-Vietnamese is a low-resource language pair, the sparse data problem is evident in the translation system of this language pair. However, it is a matter for consideration that words may or may not be segmented when translating between two languages in which spaces are not used between words, such as Chinese and Vietnamese. In machine translation, word segmentation is often done first when translating from Chinese or Vietnamese into different languages (typically English) and vice versa. Chinese and Vietnamese have the same isolated language that is, the words are not delimited by spaces.
0 kommentar(er)
