Work

A New State-of-the-Art BERT Model for Judeo-Arabic

Year: 2026

Type: conference-paper

Abstract: We present JABERT, the first BERT model pretrained specifically for historical Judeo-Arabic texts.We demonstrate that JABERT outperforms Arabic and multilingual models on the downstream task of Judeo-Arabic homograph disambiguation.Furthermore, in order to test the latter, we have curated and annotated the first Judeo-Arabic homograph test set.We release both JABERT and the Judeo-Arabic homograph test to the public for unrestricted use.

Source: Language Resources and Evaluation Conference (LREC)

DOI: 10.63317/52qpsk7c5bfc

Authors: Elisha Rosensweig, Yitzchak Lindenbaum, Hillel Gershuni, Vered Raziel-Kretzmer, Daniel Caine, Avi Shmidman

Institution: Bar-Ilan University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166517398

FWCI:

Cites:

Cited by:

Related to: 10