@incollection{GibbonHughesTrippel2024, author = {Gibbon, Dafydd and Hughes, Baden and Trippel, Thorsten}, title = {Semantic decomposition of character encodings for linguistic knowledge discovery}, booktitle = {From Data and Information Analysis to Knowledge Engineering}, editor = {Spiliopoulou, Myra and Kruse, Rudolf and Borgelt, Christian and N{\"u}rnberger, Andreas and Gaul, Wolfgang}, isbn = {978-3-540-31314-4}, doi = {10.1007/3-540-31314-1_44}, publisher = {Leibniz-Institut f{\"u}r Deutsche Sprache (IDS) [Zweitver{\"o}ffentlichung]}, pages = {366 -- 373}, year = {2024}, abstract = {Analysis and knowledge representation of linguistic objects tends to focus on larger units (e.g. words) than print medium characters. We analyse characters as linguistic objects in their own right, with meaning, structure and form. Characters have meaning (the symbols of the International Phonetic Alphabet denote phonetic categories, the character represented by the glyph '∪' denotes set union), structure (they are composed of stems and parts such as descenders or diacritics or are ligatures), and form (they have a mapping to visual glyphs). Character encoding initatives such as Unicode tend to concentrate on the structure and form of characters and ignore their meaning in the sense discussed here. We suggest that our approach of including semantic decomposition and defining font-based namespaces for semantic character domains provides a long-term perspective of interoperability and tractability with regard to data-mining over characters by integrating information about characters into a coherent semiotically-based ontology. We demonstrate these principles in a case study of the International Phonetic Alphabet.}, subject = {Bedeutung}, language = {en} }