The Road to CDLI’s Corpora Integration into CLTK: an Undertaking

This project focuses on integrating Cuneiform Digital Library Initiative (CDLI) corpora into the Classical Language Toolkit (CLTK). Currently, CLTK houses several functions developed by Dr. Willis Monroe; the difficulty in utilizing these functions is due to the variables having to be presented in a reconstructed normalized form of Akkadian, which is not how tablets are either written traditionally or stored by CDLI. The goal of this project is to enable CLTK to reconstruct a normalized spelling out of CDLI’s ATF text and thus create data available for two fundamental uses: 1) allowance of individuals to learn and practice Akkadian with real and novel reading exercises; and 2) with further class development, be analyzed on a mass scale.