Optical character recognition for ancient non-alphabetic scripts

Abstract

Optical character recognition for ancient non-alphabetic scripts Cuneiform is one of the earliest writing systems in the world, invented at the end of the fourth millennium BCE. It is usually written by pressing a stylus on moist clay tablets, creating a three-dimensional script. The script is logo-syllabic, like the Chinese or Japanese writing systems, meaning the same sign can be read logographically, as a word, as syllables, or as determinatives (ie semantic classifiers). The correct reading depends on the context. There are close to a thousand cuneiform signs, not all of which were used simultaneously; usually about 200-300 signs were used at once. This article shows Shai Gordin, Senior Lecturer at Digital Pasts Lab in Ariel University, look at the deciphering of ancient non-alphabetic scripts, and the technology we use to understand it.