Utilizing agglutinative features in Japanese-Uighur machine translation

Utilizing Agglutinative Features in Japanese-Uighur Machine Translation Muhtar MAHSUT, Yasuhiro OGAWA, Kazue SUGINO, Yasuyoshi INAGAKI Graduate School of Engineering, Nagoya University Furo-cho, Chikusa-ku, Nagoya Japan {muhtar, yasuhiro}@inagaki.nuie.nagoya-u.ac.jp Abstract Japanese and Uighur languages are agglutinative languages and they have many syntactical and morphological similarities. And roughly speaking, we can translate Japanese into Uighur sequentially by replacing Japanese words with corresponding Uighur ones after morphological analysis. However, we should translate agglutinated suffixes carefully to make correct translation, because they play important roles on both languages. In this paper, we pay attention to them and propose a Japanese-Uighur machine translation utilizing the agglutinative features of both languages. To deal with the agglutinative features, we use the derivational grammar, which makes the similarities clearer between both languages. This makes our system proposed here simple and systematical. We have implemented the machine translation system and evaluated how effectively our system works. Keywords agglutinative languages, machine translation, derivational grammar, Japanese, Uighur 1 Introduction Japanese and Uighur have many syntactical similarities, especially with respect to the word order in the sentence. This observation suggests that we can translate Japanese into Uighur in such a manner as word for word replacing after the morphological analysis of input sentences. In addition, both languages have morphological similarities, which is a significant feature of agglutinative languages. However, there is a grammatical problem, that is, Uighur grammar says that Uighur has no conjugations, while traditional Japanese grammar, which is often called school grammar, says that Japanese verbs do conjugate. Therefore the word-for-word translation based on school grammar needs to deal with verbal conjugations of Japanese, in which the translation of verbal endings is very complicated to describe. On the other hand, it is said that agglutinative language does not conjugate, and that verbal variants are derived from invariable stems by mechanically appending affixes to them. These two views contradict to each other. To resolve this problem, G. N. Kiyose proposed the derivational grammar (Kiyose, 1995) based on the phonological approach originated by Bloch (1946). This grammar claims that Japanese verbs do not conjugate and Japanese verbal variants are made up by appending suffixes to verbal stems. Because verbal conjugations need not to be considered, the derivational grammar makes morphological analysis quite simple. Since the derivational grammar pays attention to agglutinative features of languages, it is applicable to not only Japanese but also other agglutinative languages such as Uighur. So applying the derivational grammar to the two languages, we can make not only syntactical but also morphological similarities between them clearer. This approach also makes the translation simp ler and more systematic. Recently, there are many literatures that discuss translation between agglutinative languages such as Japanese and Korean (Kim et al., 1998; Lee et al., 1990). They use only syntactical similarities between them, but they can not make use of morphological similarities. Our approach systematizes both syntactical and morphological similarities between Japanese and Uighur through using the derivational grammar. In this paper, we propose a Japanese-Uighur machine translation system based on the derivational …

Content truncated to 500 words