Noun and Keyword Detection of Korean in Ubiquitous Environment

摘要

In a language, noun and keyword extraction is a key element in a ubiquitous environment. When it comes to processing Korean language information, however, there are still a lot of problems with noun and keyword extraction. This paper proposes an effective noun extraction method that considers noun emergence features. The proposed method can be effectively used in areas like information retrieval where large volumes of documents and data need to be processed in a fast manner. In this paper, a category-based keyword construction method is also presented that uses an unsupervised learning technique to ensure high volumes of queries are automatically classified. Our experimental results show that the proposed method outperformed both the supervised learning-based X~2 method known to excel in keyword extraction and the DF method, in terms of classification precision.