@inproceedings{sakr-etal-2026-auxiliary,
title = "When Does Auxiliary Classification Help Regression in Practice? A Case Study in {A}rabic Dialectness Modeling",
author = "Sakr, Abdelrahman and
Torki, Marwan and
El-Makky, Nagwa",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.30/",
pages = "639--649",
ISBN = "979-8-89176-459-0",
abstract = "Estimating the Arabic Level of Dialectness (ALDi) is a continuous regression task that quantifies how much a sentence diverges from Modern Standard Arabic (MSA). While auxiliary classification is often used to support regression, its effectiveness depends critically on how the auxiliary task is designed. We conduct a systematic study of auxiliary classification for ALDi estimation, showing that naive auxiliary supervision can degrade regression performance under skewed target distributions. We identify two key factors that determine when auxiliary tasks become beneficial: the granularity of discretization and the choice of loss function. Specifically, 7-bin discretization combined with focal loss substantially improves performance. Our approach achieves an RMSE of 0.1275 on the NADI 2024 blind test set, outperforming previous systems by over 9{\%}, and the same design transfers to English toxicity regression. Detailed error analysis reveals how auxiliary classification reshapes model behavior across the Arabic dialect spectrum. We release our code and model predictions to facilitate future research"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakr-etal-2026-auxiliary">
<titleInfo>
<title>When Does Auxiliary Classification Help Regression in Practice? A Case Study in Arabic Dialectness Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelrahman</namePart>
<namePart type="family">Sakr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marwan</namePart>
<namePart type="family">Torki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nagwa</namePart>
<namePart type="family">El-Makky</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 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Estimating the Arabic Level of Dialectness (ALDi) is a continuous regression task that quantifies how much a sentence diverges from Modern Standard Arabic (MSA). While auxiliary classification is often used to support regression, its effectiveness depends critically on how the auxiliary task is designed. We conduct a systematic study of auxiliary classification for ALDi estimation, showing that naive auxiliary supervision can degrade regression performance under skewed target distributions. We identify two key factors that determine when auxiliary tasks become beneficial: the granularity of discretization and the choice of loss function. Specifically, 7-bin discretization combined with focal loss substantially improves performance. Our approach achieves an RMSE of 0.1275 on the NADI 2024 blind test set, outperforming previous systems by over 9%, and the same design transfers to English toxicity regression. Detailed error analysis reveals how auxiliary classification reshapes model behavior across the Arabic dialect spectrum. We release our code and model predictions to facilitate future research</abstract>
<identifier type="citekey">sakr-etal-2026-auxiliary</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>639</start>
<end>649</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Does Auxiliary Classification Help Regression in Practice? A Case Study in Arabic Dialectness Modeling
%A Sakr, Abdelrahman
%A Torki, Marwan
%A El-Makky, Nagwa
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F sakr-etal-2026-auxiliary
%X Estimating the Arabic Level of Dialectness (ALDi) is a continuous regression task that quantifies how much a sentence diverges from Modern Standard Arabic (MSA). While auxiliary classification is often used to support regression, its effectiveness depends critically on how the auxiliary task is designed. We conduct a systematic study of auxiliary classification for ALDi estimation, showing that naive auxiliary supervision can degrade regression performance under skewed target distributions. We identify two key factors that determine when auxiliary tasks become beneficial: the granularity of discretization and the choice of loss function. Specifically, 7-bin discretization combined with focal loss substantially improves performance. Our approach achieves an RMSE of 0.1275 on the NADI 2024 blind test set, outperforming previous systems by over 9%, and the same design transfers to English toxicity regression. Detailed error analysis reveals how auxiliary classification reshapes model behavior across the Arabic dialect spectrum. We release our code and model predictions to facilitate future research
%U https://aclanthology.org/2026.emnlp-main.30/
%P 639-649
Markdown (Informal)
[When Does Auxiliary Classification Help Regression in Practice? A Case Study in Arabic Dialectness Modeling](https://aclanthology.org/2026.emnlp-main.30/) (Sakr et al., EMNLP 2026)
ACL