@inproceedings{tal-etal-2026-modeling,
title = "Modeling the ``Dalet'' Clitic in Historical {H}ebrew Texts: A New Prefix-Segmented {BERT} Model and Stylistic Analysis",
author = "Tal, Rachel and
Shmidman, Cheyn Shmuel and
Shmidman, Avi",
editor = {Hamilton, Sil and
{\"O}hman, Emily and
Hicke, Rebecca M. M. and
Bizzoni, Yuri and
Bax, Axel and
Matthews, Jacob A. and
H{\"a}m{\"a}l{\"a}inen, Mika},
booktitle = "Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities",
month = jul,
year = "2026",
address = "San Diego, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4dh-1.12/",
doi = "10.18653/v1/2026.nlp4dh-1.12",
pages = "121--131",
ISBN = "979-8-89176-427-9",
abstract = "The Aramaic proclitic \textit{dalet}, widely used in historical Hebrew texts, serves two distinct grammatical functions: as a subordinating conjunction and as a possessive preposition. Because these functions are orthographically identical and no annotated resources exist for this task, large-scale computational analysis of their usage has previously been infeasible. In this paper we introduce a new BERT model for historical Hebrew in which all prefixes are segmented and encoded as independent tokens. This representation allows the model to evaluate proclitics directly and provides a probe-based unsupervised method for determining the grammatical role of the \textit{dalet} clitic using masked language modeling predictions. We evaluate the approach on a manually annotated dataset drawn from historical Hebrew literature spanning multiple regions and historical periods, achieving over an average F1 score of over 0.89. Applying the method to a corpus of more than 300 million words of historical Hebrew texts, we conduct large-scale stylistic analyses of the choice between the Aramaic \textit{dalet} and available Hebrew alternatives. The results reveal geographic and diachronic trends and identify distinct stylistic clusters within the corpus. The prefix-segmented model and annotated dataset are released for unrestricted use."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tal-etal-2026-modeling">
<titleInfo>
<title>Modeling the “Dalet” Clitic in Historical Hebrew Texts: A New Prefix-Segmented BERT Model and Stylistic Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Tal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheyn</namePart>
<namePart type="given">Shmuel</namePart>
<namePart type="family">Shmidman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avi</namePart>
<namePart type="family">Shmidman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sil</namePart>
<namePart type="family">Hamilton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="given">M</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Hicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel</namePart>
<namePart type="family">Bax</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Matthews</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-427-9</identifier>
</relatedItem>
<abstract>The Aramaic proclitic dalet, widely used in historical Hebrew texts, serves two distinct grammatical functions: as a subordinating conjunction and as a possessive preposition. Because these functions are orthographically identical and no annotated resources exist for this task, large-scale computational analysis of their usage has previously been infeasible. In this paper we introduce a new BERT model for historical Hebrew in which all prefixes are segmented and encoded as independent tokens. This representation allows the model to evaluate proclitics directly and provides a probe-based unsupervised method for determining the grammatical role of the dalet clitic using masked language modeling predictions. We evaluate the approach on a manually annotated dataset drawn from historical Hebrew literature spanning multiple regions and historical periods, achieving over an average F1 score of over 0.89. Applying the method to a corpus of more than 300 million words of historical Hebrew texts, we conduct large-scale stylistic analyses of the choice between the Aramaic dalet and available Hebrew alternatives. The results reveal geographic and diachronic trends and identify distinct stylistic clusters within the corpus. The prefix-segmented model and annotated dataset are released for unrestricted use.</abstract>
<identifier type="citekey">tal-etal-2026-modeling</identifier>
<identifier type="doi">10.18653/v1/2026.nlp4dh-1.12</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4dh-1.12/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>121</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling the “Dalet” Clitic in Historical Hebrew Texts: A New Prefix-Segmented BERT Model and Stylistic Analysis
%A Tal, Rachel
%A Shmidman, Cheyn Shmuel
%A Shmidman, Avi
%Y Hamilton, Sil
%Y Öhman, Emily
%Y Hicke, Rebecca M. M.
%Y Bizzoni, Yuri
%Y Bax, Axel
%Y Matthews, Jacob A.
%Y Hämäläinen, Mika
%S Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA
%@ 979-8-89176-427-9
%F tal-etal-2026-modeling
%X The Aramaic proclitic dalet, widely used in historical Hebrew texts, serves two distinct grammatical functions: as a subordinating conjunction and as a possessive preposition. Because these functions are orthographically identical and no annotated resources exist for this task, large-scale computational analysis of their usage has previously been infeasible. In this paper we introduce a new BERT model for historical Hebrew in which all prefixes are segmented and encoded as independent tokens. This representation allows the model to evaluate proclitics directly and provides a probe-based unsupervised method for determining the grammatical role of the dalet clitic using masked language modeling predictions. We evaluate the approach on a manually annotated dataset drawn from historical Hebrew literature spanning multiple regions and historical periods, achieving over an average F1 score of over 0.89. Applying the method to a corpus of more than 300 million words of historical Hebrew texts, we conduct large-scale stylistic analyses of the choice between the Aramaic dalet and available Hebrew alternatives. The results reveal geographic and diachronic trends and identify distinct stylistic clusters within the corpus. The prefix-segmented model and annotated dataset are released for unrestricted use.
%R 10.18653/v1/2026.nlp4dh-1.12
%U https://aclanthology.org/2026.nlp4dh-1.12/
%U https://doi.org/10.18653/v1/2026.nlp4dh-1.12
%P 121-131
Markdown (Informal)
[Modeling the "Dalet" Clitic in Historical Hebrew Texts: A New Prefix-Segmented BERT Model and Stylistic Analysis](https://aclanthology.org/2026.nlp4dh-1.12/) (Tal et al., NLP4DH 2026)
ACL