Intertextual Parallel Detection in Biblical Hebrew: A Transformer-Based Benchmark

TL;DR

This paper evaluates transformer-based language models for detecting intertextual parallels in biblical Hebrew, demonstrating that models like E5 and AlephBERT can improve accuracy and efficiency in biblical scholarship.

Contribution

It introduces a benchmark for intertextual parallel detection in biblical Hebrew using transformer models, highlighting their potential in ancient text analysis.

Findings

E5 outperforms in parallel detection

AlephBERT better distinguishes non-parallel passages

Pre-trained models enhance biblical intertextual analysis

Abstract

Identifying parallel passages in biblical Hebrew (BH) is central to biblical scholarship for understanding intertextual relationships. Traditional methods rely on manual comparison, a labor-intensive process prone to human error. This study evaluates the potential of pre-trained transformer-based language models, including E5, AlephBERT, MPNet, and LaBSE, for detecting textual parallels in the Hebrew Bible. Focusing on known parallels between Samuel/Kings and Chronicles, I assessed each model's capability to generate word embeddings distinguishing parallel from non-parallel passages. Using cosine similarity and Wasserstein Distance measures, I found that E5 and AlephBERT show promise; E5 excels in parallel detection, while AlephBERT demonstrates stronger non-parallel differentiation. These findings indicate that pre-trained models can enhance the efficiency and accuracy of detecting intertextual parallels in ancient texts, suggesting broader applications for ancient language studies.