We present a new pre-trained language model (PLM) for Rabbinic Hebrew, termed Berel (BERT Embeddings for Rabbinic-Encoded Language). Whilst other PLMs exist for processing Hebrew texts (e.g., HeBERT, AlephBert), they are all trained on modern Hebrew texts, which diverges substantially from Rabbinic Hebrew in terms of its lexicographical, morphological, syntactic and orthographic norms. We demonstrate the superiority of Berel on Rabbinic texts via a challenge set of Hebrew homographs. We release the new model and homograph challenge set for unrestricted use.
@article{arxiv.2208.01875,
title = {Introducing BEREL: BERT Embeddings for Rabbinic-Encoded Language},
author = {Avi Shmidman and Joshua Guedalia and Shaltiel Shmidman and Cheyn Shmuel Shmidman and Eli Handel and Moshe Koppel},
journal= {arXiv preprint arXiv:2208.01875},
year = {2022}
}