@inproceedings{gelboim-sulem-2025-tafberta,
title = "{T}af{BERT}a: Learning Grammatical Rules from Small-Scale Language Acquisition Data in {H}ebrew",
author = "Gelboim, Anita and
Sulem, Elior",
editor = "Charpentier, Lucas and
Choshen, Leshem and
Cotterell, Ryan and
Gul, Mustafa Omer and
Hu, Michael Y. and
Liu, Jing and
Jumelet, Jaap and
Linzen, Tal and
Mueller, Aaron and
Ross, Candace and
Shah, Raj Sanjay and
Warstadt, Alex and
Wilcox, Ethan Gotlieb and
Williams, Adina",
booktitle = "Proceedings of the First BabyLM Workshop",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.babylm-main.6/",
pages = "76--90",
ISBN = "TODO",
abstract = "We present TafBERTa, a compact RoBERTa based language model tailored for Hebrew child-directed speech (CDS). This work builds upon the BabyBERTa framework to address data scarcity and morphological complexity in Hebrew. Focusing on determiner-noun grammatical agreement phenomena, we show that TafBERTa achieves competitive performance compared to large-scale Hebrew language models while requiring significantly less data and computational resources. As part of this work, we also introduce a new corpus of Hebrew CDS, HTBerman, aligned with morphological metadata and our new grammatical evaluation benchmark for Hebrew, HeCLiMP, based on minimal pairs. Our results demonstrate the effectiveness of TafBERTa in grammaticality judgments and its potential for efficient NLP in low-resource settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gelboim-sulem-2025-tafberta">
<titleInfo>
<title>TafBERTa: Learning Grammatical Rules from Small-Scale Language Acquisition Data in Hebrew</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Gelboim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elior</namePart>
<namePart type="family">Sulem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First BabyLM Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Charpentier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="given">Omer</namePart>
<namePart type="family">Gul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="given">Y</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Jumelet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Candace</namePart>
<namePart type="family">Ross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="given">Sanjay</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Warstadt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">Gotlieb</namePart>
<namePart type="family">Wilcox</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adina</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">TODO</identifier>
</relatedItem>
<abstract>We present TafBERTa, a compact RoBERTa based language model tailored for Hebrew child-directed speech (CDS). This work builds upon the BabyBERTa framework to address data scarcity and morphological complexity in Hebrew. Focusing on determiner-noun grammatical agreement phenomena, we show that TafBERTa achieves competitive performance compared to large-scale Hebrew language models while requiring significantly less data and computational resources. As part of this work, we also introduce a new corpus of Hebrew CDS, HTBerman, aligned with morphological metadata and our new grammatical evaluation benchmark for Hebrew, HeCLiMP, based on minimal pairs. Our results demonstrate the effectiveness of TafBERTa in grammaticality judgments and its potential for efficient NLP in low-resource settings.</abstract>
<identifier type="citekey">gelboim-sulem-2025-tafberta</identifier>
<location>
<url>https://aclanthology.org/2025.babylm-main.6/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>76</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TafBERTa: Learning Grammatical Rules from Small-Scale Language Acquisition Data in Hebrew
%A Gelboim, Anita
%A Sulem, Elior
%Y Charpentier, Lucas
%Y Choshen, Leshem
%Y Cotterell, Ryan
%Y Gul, Mustafa Omer
%Y Hu, Michael Y.
%Y Liu, Jing
%Y Jumelet, Jaap
%Y Linzen, Tal
%Y Mueller, Aaron
%Y Ross, Candace
%Y Shah, Raj Sanjay
%Y Warstadt, Alex
%Y Wilcox, Ethan Gotlieb
%Y Williams, Adina
%S Proceedings of the First BabyLM Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ TODO
%F gelboim-sulem-2025-tafberta
%X We present TafBERTa, a compact RoBERTa based language model tailored for Hebrew child-directed speech (CDS). This work builds upon the BabyBERTa framework to address data scarcity and morphological complexity in Hebrew. Focusing on determiner-noun grammatical agreement phenomena, we show that TafBERTa achieves competitive performance compared to large-scale Hebrew language models while requiring significantly less data and computational resources. As part of this work, we also introduce a new corpus of Hebrew CDS, HTBerman, aligned with morphological metadata and our new grammatical evaluation benchmark for Hebrew, HeCLiMP, based on minimal pairs. Our results demonstrate the effectiveness of TafBERTa in grammaticality judgments and its potential for efficient NLP in low-resource settings.
%U https://aclanthology.org/2025.babylm-main.6/
%P 76-90
Markdown (Informal)
[TafBERTa: Learning Grammatical Rules from Small-Scale Language Acquisition Data in Hebrew](https://aclanthology.org/2025.babylm-main.6/) (Gelboim & Sulem, BabyLM 2025)
ACL