Automatic Persian WordNet Construction

In this paper, an automatic method for Persian WordNet construction based on Prenceton WordNet 2.1 (PWN) is introduced. The proposed approach uses Persian and English corpora as well as a bilingual dictionary in order to make a mapping between PWN synsets and Persian words. Our method calculates a score for each candidate synset of a given Persian word and for each of its translation, it selects the synset with maximum score as a link to the Persian word. The manual evaluation on selected links proposed by our method on 500 randomly selected Persian words, shows about 76.4% quality respect to precision measure. By augmenting the Persian WordNet with the un-ambiguous words, the total accuracy of automatically extracted Persian WordNet is about 82.6% which outperforms the previously semi-automated generated Persian WordNet by about 12.6%.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Mortaza Montazery, Feshaam Faili
• Keywords: COLING 2010, Computational Linguistics, Persian WordNet, Persian WordNet Construction, Persian Words