Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Smiley, David M.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.24117
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911031572299776
author Smiley, David M.
author_facet Smiley, David M.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_24117
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intertextual Parallel Detection in Biblical Hebrew: A Transformer-Based Benchmark
Smiley, David M.
Computation and Language
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.
title Intertextual Parallel Detection in Biblical Hebrew: A Transformer-Based Benchmark
topic Computation and Language
url https://arxiv.org/abs/2506.24117