Controlled Language and the Implementation of Machine Translation for Technical Documentation

We aim at carrying out an empirical study to clarify if texts checked with a controlled language (CL) checker are indeed more translatable than other texts which are not compliant with the CL rule set, evaluating thus the degree of success of the application of such a restricted language with regard to its machine oriented features. For such an evaluation we adapt the FEMTI-Framework (Hovy et al., 2002) to our needs and divide our evaluation in two parts: selection of resources for the evaluation of a CL, and evaluation of the CL. In this article only the findings and results of the first part are presented. In order to simulate a real context of work, we use the system MULTILINT, a sophisticated language checker developed by the Institut der Gesellschaft zur Förderung der Angewandten Informationsforschung e.V. an der Universität des Saarlandes (IAI). Furthermore, we use automatic translations made with a Machine Translation System.