@inproceedings{ahmad-etal-2026-definition,
title = "Definition-Guided Learning and Root-Stratified Evaluation for {A}rabic Lexical Semantics",
author = "Ahmad, Samar and
Alharbi, Abdullah I. and
Nacar, Omer and
Altamimi, Shahad and
Assiri, Yahya",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-main.29/",
pages = "418--432",
ISBN = "979-8-89176-473-6",
abstract = "We introduce Definition-Guided Learning (DGL), a contrastive training framework that uses dictionary definitions as semantic queries and lemmas as retrieval targets, instantiated here for Arabic reverse dictionary retrieval. We construct a root-stratified Arabic lexical benchmark that limits morphological root overlap between training and test partitions. Zero-shot evaluation suggests a notable gap, with the best pre-trained model achieving only 11.16{\%} Top@1 accuracy on this benchmark. Fine-tuning with DGL yields 41.13{\%} Top@1 and NDCG@10 of 49.32{\%}, an improvement of roughly 3.7 times over the strongest zero-shot baseline we tested. Our results suggest that in-batch negative sampling tends to outperform Triplet Loss in this setting, and that definition length and lexical difficulty appear to trade off in importance across retrieval depth. These findings offer preliminary evidence that lexicographic resources can serve as a useful supervisory signal for Arabic embedding learning, at least within the scope of the benchmark studied here."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmad-etal-2026-definition">
<titleInfo>
<title>Definition-Guided Learning and Root-Stratified Evaluation for Arabic Lexical Semantics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Nacar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahad</namePart>
<namePart type="family">Altamimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yahya</namePart>
<namePart type="family">Assiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-473-6</identifier>
</relatedItem>
<abstract>We introduce Definition-Guided Learning (DGL), a contrastive training framework that uses dictionary definitions as semantic queries and lemmas as retrieval targets, instantiated here for Arabic reverse dictionary retrieval. We construct a root-stratified Arabic lexical benchmark that limits morphological root overlap between training and test partitions. Zero-shot evaluation suggests a notable gap, with the best pre-trained model achieving only 11.16% Top@1 accuracy on this benchmark. Fine-tuning with DGL yields 41.13% Top@1 and NDCG@10 of 49.32%, an improvement of roughly 3.7 times over the strongest zero-shot baseline we tested. Our results suggest that in-batch negative sampling tends to outperform Triplet Loss in this setting, and that definition length and lexical difficulty appear to trade off in importance across retrieval depth. These findings offer preliminary evidence that lexicographic resources can serve as a useful supervisory signal for Arabic embedding learning, at least within the scope of the benchmark studied here.</abstract>
<identifier type="citekey">ahmad-etal-2026-definition</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-main.29/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>418</start>
<end>432</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Definition-Guided Learning and Root-Stratified Evaluation for Arabic Lexical Semantics
%A Ahmad, Samar
%A Alharbi, Abdullah I.
%A Nacar, Omer
%A Altamimi, Shahad
%A Assiri, Yahya
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-473-6
%F ahmad-etal-2026-definition
%X We introduce Definition-Guided Learning (DGL), a contrastive training framework that uses dictionary definitions as semantic queries and lemmas as retrieval targets, instantiated here for Arabic reverse dictionary retrieval. We construct a root-stratified Arabic lexical benchmark that limits morphological root overlap between training and test partitions. Zero-shot evaluation suggests a notable gap, with the best pre-trained model achieving only 11.16% Top@1 accuracy on this benchmark. Fine-tuning with DGL yields 41.13% Top@1 and NDCG@10 of 49.32%, an improvement of roughly 3.7 times over the strongest zero-shot baseline we tested. Our results suggest that in-batch negative sampling tends to outperform Triplet Loss in this setting, and that definition length and lexical difficulty appear to trade off in importance across retrieval depth. These findings offer preliminary evidence that lexicographic resources can serve as a useful supervisory signal for Arabic embedding learning, at least within the scope of the benchmark studied here.
%U https://aclanthology.org/2026.arabicnlp-main.29/
%P 418-432
Markdown (Informal)
[Definition-Guided Learning and Root-Stratified Evaluation for Arabic Lexical Semantics](https://aclanthology.org/2026.arabicnlp-main.29/) (Ahmad et al., ArabicNLP 2026)
ACL