String Transformation Approach for Morpheme Rule Induction. (2016)

• Record Type: Journal Article
• Authors: Kovács, László; Szabó, Gábor
• Is Part Of: Procedia technology. Volume 22(2016)
• Page Start: 854
• Page End: 861
• Publication Date: 2016
• Subjects: computational linguistics -- morpheme analysis -- classification -- string transformation; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.01.060
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: Morphology is a linguistic discipline analyzing the internal components of words in expression of syntactical roles. In the case of syntetic languages, the morphemes are the primary tools to determine the meaning of the words. Due to the big variety and irregularity of morphology, it is a big challange in computational linguistics to develop an efficient learning method for induction of morpholological rules. In he presented work, the inflection rules are considered as string transformation rules and to improve the generalization property, a concept decision approach was involved into the rule induction algorithm. The proposed method supports an efficient generalization capability and it provides a better classification accuracy for untrained cases.