摘要: In this paper we present an automatic, language-independent approach to extend existing wordnet by recycling freely available bilingual resources, such as machine-readable dictionaries and on-line encyclopaedias. The is applied Slovene French. words extracted from the resources are assigned one or several synset ids based on a classifier that relies features, including distributional similarity. Automatic manual evaluation shows resulting extensions of sloWNet WOLF lexico-semantic repositories high coverage well quality.