| Resumen |
Decrypting or reconstructing extinct languages is challenging, especially when the objective is to reconstruct a language with no or very few texts left, such as the Khazar language or early Slavic and Ugric languages. In this paper, we lay out the historical perspective of the Khazar people, their language, and contemporary descendant ethnic groups, namely the Chuvash and Tatar people. Then we discuss ways Computer Science can help researchers in language reconstruction and decryption. Finally, we pilot an approach to find Khazar/Bulgar word candidates in Chuvash and Tatar languages by (1) normalizing the words of two languages and (2) comparing them, accounting for the semantic concepts to solve the homonymy problem, and (3) excluding common Turkic words and borrowings from the Russian language. © 2024 Instituto Politecnico Nacional. All rights reserved. |
