<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nacar-etal-2026-gate">
    <titleInfo>
        <title>GATE-Reranker: A Strong Arabic Cross-Encoder for Document Reranking</title>
    </titleInfo>
    <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">Omar</namePart>
        <namePart type="family">Elshehy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohamed</namePart>
        <namePart type="family">Zaytoon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Khloud</namePart>
        <namePart type="family">Al Jallad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
        </titleInfo>
        <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">Mo</namePart>
            <namePart type="family">El-Haj</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Ezzini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Arabic information retrieval increasingly relies on multi-stage pipelines in which a fast first-stage retriever produces candidate passages and a neural reranker refines relevance. While transformer cross-encoders deliver strong effectiveness through joint query–passage encoding, multilingual rerankers achieve competitive performance on Arabic benchmarks. However, systematic analysis of calibration, robustness, and deployment behavior in Arabic-specific settings remains limited. We present GATE-Reranker, a compact Arabic cross-encoder initialized from an Arabic semantic embedding backbone and fine-tuned on large-scale mMARCO-style Arabic triplets. The model scores each query–passage pair via full self-attention and a lightweight regression head, enabling plug-and-play second-stage reranking for Arabic search and RAG systems. We evaluate on three Arabic benchmarks covering binary relevance discrimination, controlled multi-negative reranking, and large-scale mMARCO evaluation. While remaining competitive with strong multilingual rerankers in ranking effectiveness, GATE-Reranker demonstrates significantly improved calibration and discriminative behavior. These properties translate into more reliable downstream performance in retrieval and RAG pipelines, while maintaining low GPU memory and latency on a Tesla T4.</abstract>
    <identifier type="citekey">nacar-etal-2026-gate</identifier>
    <identifier type="doi">10.63317/2y297wwcf77y</identifier>
    <location>
        <url>https://aclanthology.org/2026.osact-1.5/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>40</start>
            <end>48</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GATE-Reranker: A Strong Arabic Cross-Encoder for Document Reranking
%A Nacar, Omer
%A Elshehy, Omar
%A Zaytoon, Mohamed
%A Al Jallad, Khloud
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F nacar-etal-2026-gate
%X Arabic information retrieval increasingly relies on multi-stage pipelines in which a fast first-stage retriever produces candidate passages and a neural reranker refines relevance. While transformer cross-encoders deliver strong effectiveness through joint query–passage encoding, multilingual rerankers achieve competitive performance on Arabic benchmarks. However, systematic analysis of calibration, robustness, and deployment behavior in Arabic-specific settings remains limited. We present GATE-Reranker, a compact Arabic cross-encoder initialized from an Arabic semantic embedding backbone and fine-tuned on large-scale mMARCO-style Arabic triplets. The model scores each query–passage pair via full self-attention and a lightweight regression head, enabling plug-and-play second-stage reranking for Arabic search and RAG systems. We evaluate on three Arabic benchmarks covering binary relevance discrimination, controlled multi-negative reranking, and large-scale mMARCO evaluation. While remaining competitive with strong multilingual rerankers in ranking effectiveness, GATE-Reranker demonstrates significantly improved calibration and discriminative behavior. These properties translate into more reliable downstream performance in retrieval and RAG pipelines, while maintaining low GPU memory and latency on a Tesla T4.
%R 10.63317/2y297wwcf77y
%U https://aclanthology.org/2026.osact-1.5/
%U https://doi.org/10.63317/2y297wwcf77y
%P 40-48

Markdown (Informal)

[GATE-Reranker: A Strong Arabic Cross-Encoder for Document Reranking](https://aclanthology.org/2026.osact-1.5/) (Nacar et al., OSACT 2026)

• GATE-Reranker: A Strong Arabic Cross-Encoder for Document Reranking (Nacar et al., OSACT 2026)

ACL

• Omer Nacar, Omar Elshehy, Mohamed Zaytoon, and Khloud Al Jallad. 2026. GATE-Reranker: A Strong Arabic Cross-Encoder for Document Reranking. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 40–48, Palma, Mallorca (Spain). Association for Computational Linguistics.