Software Internship Report

This paper reports a five-month Internship at the Institute for Specialised Communication and Multilingualism of the interdisciplinary European Academy (EURAC) in Bolzano, Italy. Its current researches focus on specialised terminology, translation , language acquisition, minority languages and language technologies. My task was to contribute to different linguistic and educational research projects by solving linguistic and computational problems. Some projects investigate first and second language skills of South Tyrolean students, whereas another project investigates South Tyrolean computer-mediated communication. It will be shown how part of speech tagging results, which were required within these projects, were visualized in a confusion matrix using R. Furthermore an ensemble tagging tool was implemented in Python, which combines the results of different part of speech taggers and aims at the reduction of manual correction work. Additionally a python tool was developed that improves the TreeTagger's tokenization results for emoticons. In cooperation with the University of Bozen/Bolzano I created an xml learner corpus for a set of university student texts, which helps to analyze their higher literacy skills.