Corpus Bootstrapping for Syriac Linguistics

Abstract

The present article summarises a bootstrapping approach to Syriac corpus linguistics that gives freedom for Syriac researchers to apply part-of-speech (POS) tagging technology on texts of their choice using the SEDRA API mechanism and offers an annotated corpus based on this method using a representative and well-balanced selection of Syriac manuscripts spanning one millennium.

Keywords

• syriac
• pos tagging
• historical linguistics
• manuscripts