Textual Case-based Adaptation using Semantic Relatedness - A Case Study in the Domain of Security Documents

Abstract

In previous efforts graph-based and textual knowledge representations were combined for the usage in case-based reasoning. This work proposes first steps for this combination in the domain of secu- rity documents and similar document classes. We present an approach pre-processing documents for textual case-based reasoning by adapting methods of natural language processing. We propose a method improving a case-based hierarchical similarity assessment for retrieval by introducing the concept of vector space embeddings and semantic relatedness of words and phrases.