<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-celi">
    <titleInfo>
        <title>CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders.</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Crystina</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minghan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jimmy</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Bethard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In text ranking, it is generally believed that the cross-encoders already gather sufficient token interaction information via the attention mechanism in the hidden layers. However, our results show that the cross-encoders can consistently benefit from additional token interaction in the similarity computation at the last layer. We introduce CELI (Cross-Encoder with Late Interaction), which incorporates a late interaction layer into the current cross-encoder models. This simple method brings 5% improvement on BEIR without compromising in-domain effectiveness or search latency. Extensive experiments show that this finding is consistent across different sizes of the cross-encoder models and the first-stage retrievers. Our findings suggest that boiling all information into the [CLS] token is a suboptimal use for cross-encoders, and advocate further studies to investigate its relevance score mechanism.</abstract>
    <identifier type="citekey">zhang-etal-2024-celi</identifier>
    <location>
        <url>https://aclanthology.org/2024.naacl-short.16</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>188</start>
            <end>196</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders.
%A Zhang, Crystina
%A Li, Minghan
%A Lin, Jimmy
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhang-etal-2024-celi
%X In text ranking, it is generally believed that the cross-encoders already gather sufficient token interaction information via the attention mechanism in the hidden layers. However, our results show that the cross-encoders can consistently benefit from additional token interaction in the similarity computation at the last layer. We introduce CELI (Cross-Encoder with Late Interaction), which incorporates a late interaction layer into the current cross-encoder models. This simple method brings 5% improvement on BEIR without compromising in-domain effectiveness or search latency. Extensive experiments show that this finding is consistent across different sizes of the cross-encoder models and the first-stage retrievers. Our findings suggest that boiling all information into the [CLS] token is a suboptimal use for cross-encoders, and advocate further studies to investigate its relevance score mechanism.
%U https://aclanthology.org/2024.naacl-short.16
%P 188-196

Markdown (Informal)

[CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders.](https://aclanthology.org/2024.naacl-short.16) (Zhang et al., NAACL 2024)

• CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders. (Zhang et al., NAACL 2024)

ACL

• Crystina Zhang, Minghan Li, and Jimmy Lin. 2024. CELI: Simple yet Effective Approach to Enhance Out-of-Domain Generalization of Cross-Encoders.. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 188–196, Mexico City, Mexico. Association for Computational Linguistics.