Automated Bilingual Linking of Wordnet Senses

Maciej Piasecki, Roman Dyszlewski, Ewa Rudnicka

Abstract: Wordnets for different languages are linked through synsets - sets of synonymous word senses. We present a method of automated transforming synset mapping to sense mapping to build a network of translational equivalents. Two heuristics based on a cross-lingual distributional similarity model are compared with several variants of machine learning based approach exploring different descriptive features. The features are extracted from bilingual and monolingual dictionaries and distributional semantics models, interpreted against wordnets.