Construction of a Dictionary for Translating Japanese Phrases into One English Word.pdf

Construction of a Dictionary for Translating Japanese Phrases into One English Word Satoshi Shirai, Kazuhide Yamamoto and Kazutaka Takao ATR Spoken Language Translation Research Laboratories 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto, 619-0288, JAPAN E-mail: fshirai,yamamoto,ktakaog@slt.atr.co.jp Abstract In translation between languages that have dierent linguistic characteristics like Japanese and English, there are many cases in which contents are not correctly transmitted in the substitution from word to word. A method known to be eective as a measure for this is to determine the translations of verbs and nouns by using valency pattern pairs, which describe the semantic co-occurrences of verbs and nouns as valency patterns, and to pair them in the source language and the target language. However, this does not eliminate the problem of expressions regarded as ungrammatical (from the viewpoint of translation) being translated literally. In this research, we carried out analyses on expressions of compound Japanese nouns and verbs in correspondence with English words, by focusing on Japanese equivalent phrases to English words described in an English-Japanese dictionary. Consequently, there is hope that many cases of expressions created from one Japanese case element and verb corresponding to one English word can be obtained. Keywords: Japanese-English machine translation, Collocation expression, English-Japanese dictionary, Va- lency pattern 1 Introduction In the semantic analysis of machine translation, there is a need to correctly understand the co-occurrence relation- ships of words. One approach known to be eective, espe- cially in translation between languages that have dierent linguistic characteristics like Japanese and English, is the use of valency pattern pairs, which direct attention to the meaningful co-occurrences of nouns and verbs to form cor- respondences of the basic structures of expressions in the source language and the target language. I