POSTagger for ancient languages
This repository contains a workbench for
- Segmenting
- Transliteration
- POSTagging
- Translation of mainly cuneiform languages with the main focus on POSTagging.
POSTagging rules are created as regular expressions on a morphological level without taking into consideration the context of the respective word. Those rules are by no means perfect and may not be sufficient, but can provide an indication of the structure of a cuneiform text be it in its cuneiform representation (Unicode) oder in its transliteration representation.