Abstract
From a pluricentric perspective, German possesses several standard varieties, including the one used in South Tyrol (Italy). While automated lexicography has long focussed on differences of lexical forms across these varieties, meaning differences in formally identical words are more difficult to identify systematically. This study addresses such diatopic semantic variation by comparing usage patterns in corpora from Germany and South Tyrol. Using distributional evidence from word embeddings, it shows how corpus-based comparison can support lexicographic analysis by highlighting shared words whose meanings or typical contexts diverge across varieties. The focus lies on the linguistic interpretation of these patterns and on their relevance for describing variety-specific meanings. The results confirm existing lexicographic descriptions while also identifying additional candidates for future verification.