Fuzzy translation tool for linguistic terms

An automatic translation tool for linguistic terms is built. The terms are represented by fuzzy sets and the translations are based on the similarity degree between those fuzzy sets. The tool is tested on 21 adverbs in 9 languages. The fuzzy sets are constructed with a probability based approach, based on data from an International study on the choice of appropriate terms to label a noise annoyance scale. The results are in agreement with common sense translations. A detailed sensitivity analysis shows that the procedure is stable for many operator choices.