Cross-lingual conversion of lexical semantic relations: Building parallel wordnets

Parallel wordnets built upon correspondences between different languages can play a crucial role in multilingual knowledge processing. Since there is no homomorphism between pairs of monolingual wordnets, we must rely on lexical semantic relation (LSR) mappings to ensure conceptual cohesion. In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations. In particular, we propose a set of inference rules to predict Chinese wordnet structure based on English wordnet and English-Chinese translation relations. We show that this model of parallel wordnet building is effective and achieves higher precision in LSR prediction.