<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mekky-etal-2026-curriculum">
    <titleInfo>
        <title>Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ali</namePart>
        <namePart type="family">Mekky</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">El Zeftawy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lara</namePart>
        <namePart type="family">Hassan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amr</namePart>
        <namePart type="family">Keleg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Preslav</namePart>
        <namePart type="family">Nakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Morocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LahjatBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system.</abstract>
    <identifier type="citekey">mekky-etal-2026-curriculum</identifier>
    <location>
        <url>https://aclanthology.org/2026.vardial-1.22/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>261</start>
            <end>274</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models
%A Mekky, Ali
%A El Zeftawy, Mohamed
%A Hassan, Lara
%A Keleg, Amr
%A Nakov, Preslav
%S Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F mekky-etal-2026-curriculum
%X Being modeled as a single-label classification task for a long time, recent work has argued that Arabic Dialect Identification (ADI) should be framed as a multi-label classification task. However, ADI remains constrained by the availability of single-label datasets, with no large-scale multi-label resources available for training. By analyzing models trained on single-label ADI data, we show that the main difficulty in repurposing such datasets for Multi-Label Arabic Dialect Identification (MLADI) lies in the selection of negative samples, as many sentences treated as negative could be acceptable in multiple dialects. To address these issues, we construct a multi-label dataset by generating automatic multi-label annotations using GPT-4o and binary dialect acceptability classifiers, with aggregation guided by the Arabic Level of Dialectness (ALDi). Afterward, we train a BERT-based multi-label classifier using curriculum learning strategies aligned with dialectal complexity and label cardinality. On the MLADI leaderboard, our best-performing LahjatBERT model achieves a macro F1 of 0.69, compared to 0.55 for the strongest previously reported system.
%U https://aclanthology.org/2026.vardial-1.22/
%P 261-274

Markdown (Informal)

[Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models](https://aclanthology.org/2026.vardial-1.22/) (Mekky et al., VarDial 2026)

• Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models (Mekky et al., VarDial 2026)

ACL

• Ali Mekky, Mohamed El Zeftawy, Lara Hassan, Amr Keleg, and Preslav Nakov. 2026. Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models. In Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects, pages 261–274, Rabat, Morocco. Association for Computational Linguistics.