Mapping Persian Words to WordNet Synsets
Lexical ontologies are one of the main resourcesfor developing natural language processing and semantic web applications. Mapping lexical ontologies of different languagesis very important for inter-lingual tasks. On the other hand mapping approaches can be implied to build lexical ontologies for a new language based on pre-existing resources of other languages. In this paper we propose a semantic approach for mapping Persian words to Princeton WordNet Synsets. As there is no lexical ontology for Persian, our approach helps not only in building one for this language but also enables semantic web applications on Persian documents. To do the mapping, we calculate the similarity of Persian words and English synsets using their features such as super-classes and subclasses, domain and related words. Our approach is an improvement of an existing one applying in a new domain, which increases the recall noticeably.
|Year of Publication||
International Journal of Interactive Multimedia and Artificial Intelligence
Special Issue on Business Intelligence and Semantic Web
|Number of Pages||