| Korean is world famous for scientific design, would the computer processing of Korean exhibit a higher efficiency than the Chinese, English and other? Statistics made A recent breakthrough in the Analysis of language in the computer, but Korean as an agglutinative language, the syllable combination, forms a rich variety of change, this brings ahout the computer identification difficult.to solve this problem in the computer, what works should we do? With these questions, the author started writing the thesis.Through research, the paper summarized the following aspects, summarized the character encoding; how to identify, disintegrate, compose a character; how to deal with composition phenomenon; by classifying the suffix and vocabulary, idiomatic expressions, giving the corresponding identification scheme, and finally presented the design of database structure, systematically summarized the morphological types and Countermeasures of Korean studies in computer.Finally, the conclusion, confirmed the feasibility of the language research using computer, but also through the research discoveried that database expansion in quantity does not seem to make the analyzer more intelligent, but sometimes cause more ambiguity. That is to say, how to let the database structure optimized, how to let the database for better analyzer service, become the research focus of the next step. But in general, this paper provided a reference for the colleagues who are interested in computer studies of Korean, and sorted out a feasible scheme and approaches. |
