Sindhi Language Processing: A survey

Abstract

In this era of information technology, natural language processing (NLP) has become volatile field because of digital reliance of today's communities. The growth of Internet usage bringing the communities, cultures and languages online. In this regard much of the work has been done of the European and east Asian languages, in the result these languages have reached mature level in terms of computational processing. Despite the great importance of NLP science, still most of the South Asian languages are under developing phase. Sindhi language is one of them, which stands among the most ancient languages in the world. The Sindhi language has a great influence on the large community in Sindh province of Pakistan and some states of India and other countries. But unfortunately, it is at infant level in terms of computational processing, because it has not received such attention of language engineering community, due to its complex morphological structure and scarcity of language resources. Therefore, this study has been carried out in order to summarize the existing work on Sindhi Language Processing (SLP) and to explore future research opportunities, also some potential research problems. This paper will be helpful for the researchers in order to find all the information regarding SLP at one place in a unique way.