Semi-automatic annotation of semantic relations in a Swiss German sign language lexicon

Abstract

We propose an approach to semi-automatically obtaining semantic relations in Swiss German Sign Language (Deutschschweizerische Gebärdensprache, DSGS). We use a set of keywords including the gloss to represent each sign. We apply GermaNet, a lexicographic reference database for German annotated with semantic relations. The results show that approximately 60% of the semantic relations found for the German keywords associated with 9000 entries of a DSGS lexicon also apply for DSGS. We use the semantic relations to extract sub-types of the same type within the concept of double glossing (Konrad 2011). We were able to extract 53 sub-type pairs.