01460nas a2200217   4500000000100000000000100001008004100002260001200043653002100055653001200076653002200088653001500110100002300125700002400148245004500172856007000217300000900287490000600296520092600302022001401228       2009                            d  c12/200910aSemantic Lexicon10aWordNet10aAutomatic Mapping10aOntologies1 aRahim Dehkharghani1 aMehrnoush Shamsfard00aMapping Persian Words to WordNet Synsets  uhttp://www.ijimai.org/journal/sites/default/files/IJIMAI1-2-2.pdf  a6-130 v13 aLexical 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.  a1989-1660