An automatic transcription system for Arabic numerals in Korean

We have proposed Auto-TAN, an automatic transcription system of Arabic numerals into Korean alphabetic letters using linguistic rules and clues. Few previous studies have previously discussed the problems in transcribing Arabic numerals into Korean text. We have suggested detailed NRF (number reading formula) paradigms, analyzed the structure of NUMEs (numerical expressions) and components in a larger scope, and investigated compatibilities and selection rules among those components. Based on these linguistic features, 13 stereotyped patterns, 16 rules and 63 clues determining NRF types are formulated for Auto-TAN. This system works modularly in 5 steps. The pilot test was conducted with a test suite which contains 56782 NUMEs. Encouraging results of 84.8% and 10.5% accuracy were obtained for unique transcription and multiple transcriptions, respectively.