GI-tutor: grammar-checking for (Italian) students of German

Computers have played a significant role in second language learning as they can offer different types of language activities and provide learners with immediate and appropriate feedbacks. In ICALL systems, learning is activated by focusing the learner's attention to the correct form and comparing it to the wrong one. Feedback offers an explicit explanation of the mistakes made by the student. The focus of this paper is a grammar checker designed for Italian native speakers learning German GI-tutor. The system's structure was taken from a previous study [28] and enforced to analyse a conspicuous number of sentences, with different sentence and phrase structures. The lexicon used has been manually organized at the beginning, with some 8,000 entries overall; then, an enlargement has been obtained through an adaptation of the lexicon made available by Hamburg University Constraint Dependency Grammar (JWCDG) and downloaded from their website. A corpus containing wrong sentences was expanded by extracting data from exams written by first-year students of the German course at the University Ca' Foscari. The errors were then classified in order to obtain a general statistical analysis of the main problems encountered when learning German. Attention was given also to parsers and their use and functionality in language learning. Furthermore, the performance of the constituency grammar checker was evaluated to determine the types and frequencies of errors it can successfully diagnose. This was done by comparing it to ParZu a generic German dependency parser developed at the University of Zürich and to Stanford Parser for German.