The 18th World Congress of Jewish Studies

Identifying Islamic Sources of Judeo–Arabic Texts via Semi- Automated Transliteration and Text Reuse Detection: New Findings on “Duties of the Heart”

While Arabic and Islamic Digital Humanities research is rapidly developing due to wide interest and ground-breaking developments in corpus building and natural language processing (NLP) tools, such as OpenITI, Kitab, CAMeL etc, Judeo-Arabic research is lagging. Tools available today for Judeo-Arabic scholars do not meet the same standards in terms of open data and flexibility.
The lecture will present a pipeline enabling Judeo-Arabic scholars to search the Arabic and Islamic databases, by incorporating a Judeo-Arabic – Arabic interface with text reuse detection tools.
The benefits of this approach will be demonstrated by new identifications of Islamic quotations in Bahya’s “Duties of The Hearts”. Discoveries achieved by applying the tools developed in this research over a large Islamic corpus (OpenITI).