This book aims at emphasizing the importance of using computational methods for restoring and understanding lost historical textual documents. Historical textual documents, whether they are simple stories, or religious scriptures, or even scientific writings, can be reasonably reconstructed with the help of computational techniques. Nowadays, the manual process of scholarly editing has been considerably alleviated with the help of intelligent software packages. Till date, existing software packages can mainly collate (compare) the witnesses, but do not compute automatically a base text, and propose an archetype of the lost text. This research explains how the determination of a base text could be converted to a categorization and classification problem, thereby facilitating the restoration of the original text with the help of a novel algorithm.

Mohamadou Nassourou is an electrical and computer engineer. He has been working as software developer and scientific researcher for over a decade now.