Automatic dialect identification is a necessary Language Technology for processing multidialect languages in which the dialects are linguistically far from each other. Particularly, this becomes crucial where the dialects are mutually unintelligible. Therefore, to perform computational activities on these languages, the system needs to identify the dialect that is the subject of the process. Kurdish language encompasses various dialects. It is written using several different scripts. The language lacks of a standard orthography. This situation makes the Kurdish dialectal identification more interesting and required, both form the research and from the application perspectives. In this research, we have applied a classification method, based on supervised machine learning, to identify the dialects of the Kurdish texts. The research has focused on two widely spoken and most dominant Kurdish dialects, namely, Kurmanji and Sorani. The approach could be applied to the other Kurdish dialects as well. The method is also applicable to the languages which are similar to Kurdish in their dialectal diversity and differences.

This research suggests a method for machine translation among two Kurdish dialects. We chose the two widely spoken dialects, Kurmanji and Sorani, which are considered to be mutually unintelligible. Also, despite being spoken by about 30 million people in different countries, Kurdish is among less-resourced languages. The research used bi-dialectal dictionaries and showed that the lack of parallel corpora is not a major obstacle in machine translation between the two dialects. The experiments showed that the machine translated texts are comprehensible to those who do not speak the dialect. The research is the first attempt for inter-dialect machine translation in Kurdish and particularly could help in making online texts in one dialect comprehensible to those who only speak the target dialect. The results showed that the translated texts are in 71% and 79% cases rated as understandable for Kurmanji and Sorani respectively. They are rated as slightly understandable in 29% cases for Kurmanji and 21% for Sorani.

No abstract

Cit a tio n Silv a, E.S. a n d G h o d si, M . a n d H a s s a ni, H . a n d Ab b a si r a d , K. (2 0 1 6) A q u a n ti t a tiv e e x plo r a tio n of t h e s t a ti s tic al a n d m a t h e m a ti c al k n o wl e d g e of u niv e r si ty e n t r a n t

Currently, no offline tool is available for Optical Character Recognition (OCR) in Kurdish. Kurdish is spoken in different dialects and uses several scripts for writing. The Persian/Arabic script is widely used among these dialects. The Persian/Arabic script is written from Right to Left (RTL), it is cursive, and it uses unique diacritics. These features, particularly the last two, affect the segmentation stage in developing a Kurdish OCR. In this article, we introduce an enhanced character segmentation based method which addresses the mentioned characteristics. We applied the method to text-only images and tested the Kurdish OCR using documents of different fonts, font sizes, and image resolutions. The results of the experiments showed that the accuracy rate of character recognition of the proposed method was 90.82% on average.