arXiv:2606.19638v1 Announce Type: new Abstract: Textual reuse pervades the Hebrew Bible, yet the computational methods used to detect it still rest largely on lexical overlap, and they falter once a parallel involves paraphrase, lexical substitution, or syntactic reworking. This paper introduces MiqraBERT, a Sentence-BERT model finetuned from AlephBERT (a Modern Hebrew encoder) for verse-level semantic similarity in Biblical Hebrew. The training set comprises 1,650 labeled verse and half-verse pairs: 825 true parallels drawn from the Chronicles synoptic material and from foundational studies o
The continuous advancements in AI, particularly in natural language processing and transformer models, are enabling increasingly specialized applications for textual analysis.
This development highlights the growing capability of AI to handle complex semantic tasks in niche linguistic domains, extending AI's utility beyond mainstream languages and applications.
AI models are becoming more adept at understanding and identifying textual reuse, even with paraphrasing and stylistic changes, for ancient and less-resourced languages.
- · Biblical scholars
- · Digital humanities researchers
- · AI researchers in NLP
- · Traditional manual textual analysis methods
Improved detection of textual reuse and intertextuality in ancient biblical texts becomes possible.
This methodology could be adapted for other ancient languages or highly specialized linguistic analysis, expanding the scope of AI applications.
Enhanced AI understanding of ancient texts could lead to new insights into historical writing practices, cultural exchange, and even the evolution of language itself.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL