Comparison of distance measures for historical spelling variants

Abstract

This paper describes the comparison of selected distance measures in their applicability for supporting retrieval of historical spelling variants (hsv). The interdisciplinary project Rule-based search in text databases with nonstandard orthography develops a fuzzy full-text search engine for historical text documents. This engine should provide easier text access for experts as well as interested amateurs. The FlexMetric framework enhances the distance measure algorithm found to be most efficient according to the results of the evaluation. This measure can be used for multiple applications, including searching, post-ranking, transformation and even reflection about one's own language. © 2006 International Federation for Information Processing.