Measuring the Similarity between Compound Nouns in Different Languages Using Non-Parallel Corpora

This paper presents a method that measures the similarity between compound nouns in different languages to locate translation equivalents from corpora. The method uses information from unrelated corpora in different languages that do not have to be parallel. This means that many corpora can be used. The method compares the contexts of target compound nouns and translation candidates in the word or semantic attribute level. In this paper, we show how this measuring method can be applied to select the best English translation candidate for Japanese compound nouns in more than 70% of the cases.