@inproceedings{nikolova-stoupak-etal-2026-bereshit,
title = "{BER}eshi{T}: an {A}ncient {H}ebrew Model based on {D}icta{BERT}",
author = "Nikolova-Stoupak, Iglika and
Amblard, Maxime and
Rey, Fr{\'e}d{\'e}rique",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.7/",
doi = "10.63317/4j3oje5q7bcd",
pages = "72--88",
abstract = "This project addresses the general absence of Natural Language Processing (NLP) tools when it comes to historical languages as a subset of low-resource languages that is relevant to an array of academic disciplines from linguistics to textual criticism. In particular, we train an Ancient Hebrew language model, BEReshiT, as well as BEReshiT-morph, a submodel for morphological annotation. BEReshiT is achieved through the fine-tuning of DictaBERT, a state-of-the-art model for Modern Hebrew that has also proved useful in Biblical Hebrew tasks. Layer freezing is applied in order to achieve maximal results and gain insight about the adaptation process. In the context of an elaborate cloze test, BEReshiT demonstrates increased performance and notions of the Ancient Hebrew language compared to the source model as well as a selection of additional relevant models. The submodel BEReshiT-morph performs highly on tasks of morphological classification, reaching an F1 score of 0.97 for part-of-speech (POS) tagging. We will release the main and morphological models as well as the datasets used at training and evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikolova-stoupak-etal-2026-bereshit">
<titleInfo>
<title>BEReshiT: an Ancient Hebrew Model based on DictaBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iglika</namePart>
<namePart type="family">Nikolova-Stoupak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxime</namePart>
<namePart type="family">Amblard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédérique</namePart>
<namePart type="family">Rey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This project addresses the general absence of Natural Language Processing (NLP) tools when it comes to historical languages as a subset of low-resource languages that is relevant to an array of academic disciplines from linguistics to textual criticism. In particular, we train an Ancient Hebrew language model, BEReshiT, as well as BEReshiT-morph, a submodel for morphological annotation. BEReshiT is achieved through the fine-tuning of DictaBERT, a state-of-the-art model for Modern Hebrew that has also proved useful in Biblical Hebrew tasks. Layer freezing is applied in order to achieve maximal results and gain insight about the adaptation process. In the context of an elaborate cloze test, BEReshiT demonstrates increased performance and notions of the Ancient Hebrew language compared to the source model as well as a selection of additional relevant models. The submodel BEReshiT-morph performs highly on tasks of morphological classification, reaching an F1 score of 0.97 for part-of-speech (POS) tagging. We will release the main and morphological models as well as the datasets used at training and evaluation.</abstract>
<identifier type="citekey">nikolova-stoupak-etal-2026-bereshit</identifier>
<identifier type="doi">10.63317/4j3oje5q7bcd</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.7/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>72</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BEReshiT: an Ancient Hebrew Model based on DictaBERT
%A Nikolova-Stoupak, Iglika
%A Amblard, Maxime
%A Rey, Frédérique
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F nikolova-stoupak-etal-2026-bereshit
%X This project addresses the general absence of Natural Language Processing (NLP) tools when it comes to historical languages as a subset of low-resource languages that is relevant to an array of academic disciplines from linguistics to textual criticism. In particular, we train an Ancient Hebrew language model, BEReshiT, as well as BEReshiT-morph, a submodel for morphological annotation. BEReshiT is achieved through the fine-tuning of DictaBERT, a state-of-the-art model for Modern Hebrew that has also proved useful in Biblical Hebrew tasks. Layer freezing is applied in order to achieve maximal results and gain insight about the adaptation process. In the context of an elaborate cloze test, BEReshiT demonstrates increased performance and notions of the Ancient Hebrew language compared to the source model as well as a selection of additional relevant models. The submodel BEReshiT-morph performs highly on tasks of morphological classification, reaching an F1 score of 0.97 for part-of-speech (POS) tagging. We will release the main and morphological models as well as the datasets used at training and evaluation.
%R 10.63317/4j3oje5q7bcd
%U https://aclanthology.org/2026.lt4hala-1.7/
%U https://doi.org/10.63317/4j3oje5q7bcd
%P 72-88
Markdown (Informal)
[BEReshiT: an Ancient Hebrew Model based on DictaBERT](https://aclanthology.org/2026.lt4hala-1.7/) (Nikolova-Stoupak et al., LT4HALA 2026)
ACL
- Iglika Nikolova-Stoupak, Maxime Amblard, and Frédérique Rey. 2026. BEReshiT: an Ancient Hebrew Model based on DictaBERT. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 72–88, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).