Synonyms are a highly relevant information source for natural language processing. Automatic synonym extraction methods have in common that they are either applied on the surface representation of the text or on a syntactical structure derived from it. In this paper, however, we present a semantic synonym extraction approach that operates directly on semantic networks (SNs), which were derived from text by a deep syntactico-semantic analysis. Synonymy hypotheses are extracted from the SNs by graph matching. These hypotheses are then validated by a support vector machine (SVM) employing a combined graph and string kernel. Our method was compared to several other approaches and the evaluation has shown that our results are considerably superior.
展开▼
