A preliminary study of croatian lexical substitution

Abstract

Lexical substitution is a task of determining a meaning-preserving replacement for a word in context. We report on a preliminary study of this task for the Croatian language on a small-scale lexical sample dataset, manually annotated using three different annotation schemes. We compare the annotations, analyze the inter-annotator agreement, and observe a number of interesting language-specific details in the obtained lexical substitutes. Furthermore, we apply a recently-proposed, dependency-based lexical substitution model to our dataset. The model achieves a P@3 score of 0.35, which indicates the difficulty of the task.