A Novel Parts of Speech (POS) Tagset for morphological, syntactic and lexical annotations of Saraiki language

One of the important resources required for various Natural Language Processing (NLP) applications like machine translation, information retrieval and text mining, is annotated corpora. Text corpora annotation process requires parts speech (POS) tags to mark different with grammatical annotations in order identify linguistic properties a word, sentence or discourse. The marking items based on two main features 1) category 2) context (word, discourse) i.e. relationship adjacent related text. Saraiki being one oldest languages still resource scarce language recorded literature as well computational context. According our study, at present, there no tagset defined language. This work presents first hierarchical POS (MPOST) tag set which designed be used morphological, syntactic lexical