Enriching Slovene WordNet with domain-specific terms

Abstract

The paper describes an innovative approach to expanding the domain coverage of wordnet by exploiting multiple resources. In the experiment described here we are using a large monolingual Slovene corpus of texts from the domain of informatics to harvest terminology from, and a parallel English-Slovene corpus and an online dictionary as bilingual resources to facilitate the mapping of terms to the Slovene Wordnet. We first identify the core terms of the domain in English using the Princeton Wordnet, and then we translate them into Slovene using a bilingual lexicon produced from the parallel corpus. In the next step we extract multi-word terms from the Slovene domain-specific corpus using a hybrid approach, and finally match the term candidates to existing Wordnet synsets.  The proposed method appears to be a successful way to improve the domain coverage of Wordnet as it yields abundant term candidates and exploits various multilingual resources.