A Rule Based Approach for Japanese-Uyghur Machine Translation System

A Rule Based Approach for Japanese-Uyghur Machine Translation System

Maimitili Nimaiti (Nagoya Institute of Technology, Nagoya, Japan) and Yamamoto Izumi (Nagoya Institute of Technology, Nagoya, Japan)
DOI: 10.4018/ijssci.2014010104
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Japanese Uyghur machine translation system has been designed and developed using recent rule based approach. Even though Japanese and Uyghur language has many similarities, but there are also some linguistic differences cause serious problems to the word for word translation. In fact, as straightforward word-for-word Japanese-Uighur translation sometimes yields unnatural Uighur sentences. To raise the translation accuracy, the authors propose a word-for-word translation system using subject verb agreement in Uighur. After a brief introduction to the comparative study of Japanese-Uyghur grammars, morphology and syntax, the authors explain their developing of a word to word rule base system. The coverage of this rule base system, the rules for translation, comparison of experimental result between statistical machine translation system and rule base machine translation system are explained. Some practical suffix translation methods solving problems in Uyghur language are also proposed.
Article Preview

2. Grammatical Comparisons Of Japanese And Uighur

Uyghur, like all the other Turkic languages, has a word order of subject+object+verb (SOV), and is considered to be an agglutinative language with very productive inflectional and derivational suffixation process in which a sequence of inflectional and derivational morphemes get affixed to a word stem. In Uyghur, a verb could have hundreds of word forms by sequentially adding different affixes to the word stem. Japanese, which is also considered to be an agglutinative language, also has the same word order and morphological features as Uyghur. Some researches show that this morphological and syntactic closeness is sufficient to obtain a relatively good translation result from Japanese into Uyghur on a transfer approach (Yasuhiro Ogawa,2000; Polat Kadir,2004). In the following sections, we will make a comparison between Japanese and Uyghur in two different levels: morphology and syntax with a close attention focused on their differences.

2.1. Morphological Comparison

As we compare the word formation, we could find that in both Japanese and Uighur, word forms are generated by attaching many suffixes denoting case, mood, person, tense, etc. to one word stem as seen in Example(1).

(1)kuralmiganliktin(“as it was not seen”)
kur + al +mi+ghan + liqtin
(見ら  れ  な かった    ので)
kur/見ら(see):stem
+al/れ:passive voice
+mi/な:negation
+ghan/かった:past tense
+liqtin/ので:causal form

Generally, Japanese and Uyghur share a significant amount of morphological and syntactic features in common. However, there are also some differences in word formation of nouns, verbs, etc. In the following sections we will take a look at some aspects of word forming where Japanese and Uyghur differs.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing