Developing a tagset for Pashto part of speech tagging

While building a machine translation system, the embedded part-of-speech (POS) tagger deserves special attention. The ever first tagset discussed here is created in accordance with the EAGLES guidelines. These guidelines were written for the languages of European Union. They can also be applied to Pashto language. This paper presents the creation process of Pashto tagset, which helps in the development of a POS tagger.