Semantic Web based Machine Translation

This paper describes the experimental combination of traditional Natural Language Processing (NLP) technology with the Semantic Web building stack in order to extend the expert knowledge required for a Machine Translation (MT) task. Therefore, we first give a short introduction in the state of the art of MT and the Semantic Web and discuss the problem of disambiguation being one of the common challenges in MT which can only be solved using world knowledge during the disambiguation process. In the following, we construct a sample sentence which demonstrates the need for world knowledge and design a prototypical program as a successful solution for the outlined translation problem. We conclude with a critical view on the developed approach.