Research Of The Polysemy In Tibetan For Information Processing

Throughout the development process for 40 years,currently the focus of Tibetan information processing have changed from the processing of Tibetan “characters” to that of morphology,syntax,pragmatics and discourse etc,therefore,in the field of Tibetan information processing,the research on concrete characteristics of all sorts of words and sentences and the construction of all kinds of corpus or knowledge bases always absorb much attention.As a linguistic phenomenon ubiquitous in many languages,polysemy is also the corollary of language development,which exists in the ancient Tibetan as well and has brought much convenience to verbal communication of people.However,observed from the angle of language information processing,the linguistic phenomenon of polysemy causes too much trouble in Tibetan information processing.Although it belongs to the basic research,the study polysemy in Tibetan information processing is also related to many fields such as cognitive linguistics,lexicology,semantics and information processing etc.From the angle of information processing,the polysemy phenomenon in Tibetan is analyzed and studied in this paper,which is composed of five parts as follows.Firstly,the background and current situation in polysemy research of Tibetan are analyzed from the three aspects like traditional grammar of Tibetan,modern Tibetan and information processing,and the ideas and innovation points of this paper are presented.Secondly,according to the theories of modern linguistics,lexicology and cognitive science etc,the related concepts of polysemy of Tibetan are further elaborated,and the linguistic features and occurrence approach of polysemy are analyzed.Thirdly,the ambiguity problem,which is the dilemma in studying Tibetan information processing caused by polysemy of Tibetan,is analyzed with examples.In the fourth part,according to the types of ambiguity induced by polysemy,three solutions of ambiguity are proposed.Finally,the construction and application of “Corpus for Polysemy of Verbs in Tibetan” are investigated.The research of this paper is of important practical significance to such aspects of Tibetan information processing as the word segmentation method,machine translation,information retrieval and lexicography,and it also provides language data,technical support and implementation patterns for constructing the knowledge base of polysemy of Tibetan and contribute to further promotion of Tibetan language research.