Affiliations:
Department of Computer Engineering, Sari Branch, Islamic Azad University, Sari, Iran
Correspondence:
[*]
Corresponding author. Homayun Motameni, Department of Computer Engineering, Sari Branch, Islamic Azad University, Sari, Iran. Tel./Fax: +98 9111140554; E-mail: [email protected].
Abstract: Given the ability of fuzzy systems to make decisions in uncertainties such as morphology, and the huge number of studies conducted on morphology, this study first suggests a fuzzy morphology; then, it discusses the effectiveness of types of N-gram labeling methods to identify the role of words in Persian compounds. To find the optimal labeling, then, a new hybrid method is expressed for N-gram labeling. In relation to compound sentences, two independent roles including subject, governing predicate, predicate, object and complement and dependent roles including noun, adverb, governing genitives, genitives, bending, retroactive, apposition, exclamation and annunciator are studied. To compare the success rate of the proposed fuzzy method, existing HMM (hidden Markov model) is studied to identify the role of words in three different label types. The results of this comparison showed that the success rates of hybrid labeling and Bi-gram labeling are closed in both models. Thus, these two methods have been successful in both morphological models compared to Uni-gram labeling. It is worth noting, the highest success rate was related to fuzzy morphology and Bi-gram labeling.
