Open AccessEvaluation of inkurdish Machine Translation System
Author(s) -
kanaan mikael Kaka-Khan,
Fatima Jalal Taher
Publication year - 2017
Publication title -
govarî zankoy geşepedanî miroyî
Language(s) - English
Resource type - Journals
eISSN - 2411-7765
pISSN - 2411-7757
DOI - 10.21928/juhd.v3n2y2017.pp862-868
Subject(s) - machine translation , example based machine translation , computer science , machine translation software usability , natural language processing , artificial intelligence , evaluation of machine translation , point (geometry) , translation (biology) , transfer based machine translation , dynamic and formal equivalence , rule based machine translation , computer assisted translation , field (mathematics) , synchronous context free grammar , linguistics , mathematics , biochemistry , chemistry , philosophy , geometry , messenger rna , pure mathematics , gene
Lack of having a perfect machine translation for Kurdish language is a huge gap in Kurdish Language processing (KNLP). inkurdish is a first machine translation system for Kurdish language which is capable of translating English into Kurdish sentences. Building "inkurdish" machine translation system was a great point regarding Kurdish language processing, but like any other translation system has strengths as well as many shortcomings and issues. This paper tries to evaluate inkurdish machine translation system according to both linguistics and computational issues. It might help any other researchers interested in doing research in this field. It attempts to evaluate inKurdish from different perspectives, such as, giving un common words, sentences, phrases and paragraphs in this machine to check whether it provides the correct translation or not. A general evaluation can be done after getting a valid sample with their translations from the machine and compared to the meanings of the words outside the machine.