Building a Japanese-Chinese Dictionary Using Kanji/Hanzi Conversion

Building a Japanese-Chinese Dictionary Using Kanji/Hanzi Conversion Chooi-Ling Goh, Masayuki Asahara, and Yuji Matsumoto Graduate School of Information Science, Nara Institute of Science and Technology, 8916-5 Takayama, Ikoma, Nara 630-0192, Japan {ling-g, masayu-a, matsu}@is.naist.jp Abstract. A new bilingual dictionary can be built using two existing bilingual dictionaries, such as Japanese-English and English-Chinese to build Japanese-Chinese dictionary. However, Japanese and Chinese are nearer languages than English, there should be a more direct way of doing this. Since a lot of Japanese words are composed of kanji, which are similar to hanzi in Chinese, we attempt to build a dictionary for kanji words by simple conversion from kanji to hanzi. Our survey shows that around 2/3 of the nouns and verbal nouns in Japanese are kanji words, and more than 1/3 of them can be translated into Chinese directly. The accuracy of conversion is 97%. Besides, we obtain translation candidates for 24% of the Japanese words using English as a pivot language with 77% accuracy. By adding the kanji/hanzi conversion method, we increase the candidates by 9%, to 33%, with better quality candidates. 1 Introduction R. Dale et al. (Eds.): IJCNLP 2005, LNAI 3651, pp. 670–681, 2005. c ⃝ Springer-Verlag Berlin Heidelberg 2005 Bilingual dictionaries have unlimited usage. In order for one to learn a new lan- guage, a bilingual dictionary can never be absent. In natural language process- ing community, bilingual dictionaries are useful in many areas, such as machine translation and cross language information retrieval. In this research, we attempt to build a Japanese-Chinese dictionary using public available resources. There are already some existing Japanese-Chinese dictionaries, such as Shogakukan’s Ri-Zhong Cidian [1], but they are not publicly available in electronic form. Our purpose is to build an electronic dictionary from public resources and make it public available. The first dictionary that we use is IPADIC [2], a Japanese dictionary used by ChaSen [3], a Japanese morphological analyzer. We extract only nouns, verbal nouns and verbs from this dictionary, and try to search for their translation equivalents in Chinese. One can build a new bilingual dictionary for a new pair of languages using two bilingual lexicons [4–8]. Since it is always easier to get bilingual dictionaries that involve English as one of the languages, using English as a pivot language is pos- sible. In this case, we first look for the English translations of one language, and then try to find the possible candidates in the other language through English. Then we rank the candidates according to the similarities between the two words Building a Japanese-Chinese Dictionary Using Kanji/Hanzi Conversion 671 using some linguistic knowledge and statistical information. In our research, we make use of two public resources, EDICT [9] - a Japanaese-English dictionary and CEDICT [10] - a Chinese-English dictionary, to create the new language pair Japanese-Chinese dictionary using English as a pivot language. We obtain 77% accuracy. However, this method extracts only translations for about 24% of the Japanese words in IPADIC because the EDICT and CEDICT dictionaries are …

Content truncated to 500 words