The application of natural language processing (NLP) tools in relation to selected Mongolic languages: review of the current literature, available NLP tools and outlooks for the future

This paper tackles the problem of the selected Mongolic languages: Khamnigan Mongol, Oirat Mongol and Dagur spoken in Russia, Mongolia and China. The aim of this presentation is to answer the following questions: What is the current sociolinguistic condition of these languages and which NLP tools have been applied to which Mongolic languages so far? The presented paper will demonstrate that the development of the NLP tools for the family of Mongolic languages started only recently and refers mostly to the information retrieval (IR) tasks and topics which are related to it, such as applying stemming and stoplist in IR, keyword retrieval system for locating words in historical Mongolian document images, n-gram-based retrieval units and speech recognition tools devoted to the Mongolian phenomenon of vowel harmony.