Historical languages and digital texts

TBA from forthcoming blog post

Digital Classics

TBA from forthcoming blog post

Current challenges

We need digital editions that we can study computationally as easily as scholars of English literature can study digital texts in English. Two barriers that remain as high today as they were in the 1990s are

  1. the orthography of polytonic Greek. Unicode Greek is a hot mess.

  2. Greek morphology. Greek morphology is complex, and due to the ways accent and morphology interact, cannot be analyzed with the standard technology of finite state transducers.

In the following two sections, I present develop an approach to removing those barriers.