Summary
Methods of automated indexing make use of indices with words to be sought. Mistakes made in the input text normally prevent the search to be successful. Therefore an investigation of a likely use of transformations was made in order to consider the most possible variants of spelling without allowing a great loss in the precision of indexing. For this purpose different groups of phonetic transformations were defined. Their effects were examined in regard to two different random samples of input texts: one of them consisting of texts which had to be successfully indexed, the other exclusively with examples to be rejected by the indexing algorithm. Some transformations were proven to be useful. Yet with them only the phonetical spelling errors (a small part of all occurring errors) are covered. Furthermore, significantly longer response times result. Therefore phonetic transformations benefit only when a method puts its main emphasis on a high degree of automation. On the contrary, if a semi-automated method is used, a well defined list of indexed alternatives which regards single errors in the input texts leads to an acceptable solution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
BRIGL, B. (1992): Eine Methode zur automatischen lexikabasierten Indexierung von Diagnosen (LBI-Methode). Report 1/1992 of Institut für Medizinische Biometrie und Informatik, Heidelberg.
DAVIDSON, L. (1962): Retrieval of Misspelled Names in an Airline Passenger Record System. Comm. Ass. comput. Machin., 5, 169–171.
FISCHER, R.-J. (1980): Automatische Schreibfehlerkorrektur in Texten. Springer, Heidelberg.
FISCHER, R.-J. (1991): Vergleich verschiedener Methoden der Abbildung medizinischer Aussagen auf Texte einer standardisierten Terminologie. In: K. Überla, O. Rienhoff, and N. Victor (eds.): Quantitative Methoden in der Epidemiologie, Medizinische Informatik und Statistik, 72. Springer, Heidelberg, 253–257.
FISCHER, R.-J. (1993): Pseudoroots as Descriptors for a Thesaurus Based on Weidtman’s Diagnosis Table of Pediatrics. In: O. Opitz, B. Lausen, and R. Klar (eds.): Information and Classification — Concepts, Methods and Applications. Springer, Heidelberg (in print)
GREENFIELD, R.H. (1977): An Experiment to Measure the Performance of Phonetic Key Compression Retrieval Schemes. Meth. Inform. Med., 16, 230–233.
HERGET, M. (1966): Verwendung der Phonetik im Rahmen einer elektronischen Datenverarbeitungsanlage. Kriminalistik, 20, 216
JOSEPH, D.M., and WONG, R.L. (1979): Correction of Misspellings and Typographical Errors in a Free-Text Medical English Information Storage and Retrieval System. Meth. Inform. Med., 18, 228–234.
POSTEL, H.J. (1969): Die Kölner Phonetik. IBM-Nachrichten, 198, 925–931.
RUSSELL, R.C. (1922): U.S. Patent 1,435,663
WEIDTMAN, V. (1989): Diagnoscschiiissei für die Pädiatrie. Springer, Heidelberg.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin · Heidelberg
About this paper
Cite this paper
Fischer, RJ. (1994). Methods of Phoneticizing in Regard to Spelling Variants of Medical Phrases. In: Bock, HH., Lenski, W., Richter, M.M. (eds) Information Systems and Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-46808-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-46808-7_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58057-7
Online ISBN: 978-3-642-46808-7
eBook Packages: Springer Book Archive