A Novel Approach to Semantic Indexing Based on Concept

This paper suggests the efficient indexing method based on a concept vector space that is capable of representing the semantic content of a document. The two information measure, namely the information quantity and the information ratio, are defined to represent the degree of the semantic importance within a document. The proposed method is expected to compensate the limitations of term frequency based methods by exploiting related lexical items. Furthermore, with information ratio, this approach is independent of document length.

• Type: Conference
• Year: 2003
• Where: ACL
• Authors: Bo-Yeong Kang
• Keywords: ACL 2003, ACL 2007, Concept Vector Space, Efficient Indexing Method, Information Ratio