<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2024-jina">
    <titleInfo>
        <title>Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Han</namePart>
        <namePart type="family">Xiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rohan</namePart>
        <namePart type="family">Jha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jonne</namePart>
            <namePart type="family">Sälevä</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Abraham</namePart>
            <namePart type="family">Owodunni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT’s late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this paper, we introduce a novel architecture and a training framework to support long context window and multilingual retrieval. Leveraging Matryoshka Representation Loss, we further demonstrate that the reducing the embedding dimensionality from 128 to 64 has insignificant impact on the model’s retrieval performance and cut storage requirements by up to 50%. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks,</abstract>
    <identifier type="citekey">xiao-etal-2024-jina</identifier>
    <location>
        <url>https://aclanthology.org/2024.mrl-1.11</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>159</start>
            <end>166</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
%A Xiao, Han
%A Wang, Bo
%A Jha, Rohan
%Y Sälevä, Jonne
%Y Owodunni, Abraham
%S Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F xiao-etal-2024-jina
%X Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT’s late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this paper, we introduce a novel architecture and a training framework to support long context window and multilingual retrieval. Leveraging Matryoshka Representation Loss, we further demonstrate that the reducing the embedding dimensionality from 128 to 64 has insignificant impact on the model’s retrieval performance and cut storage requirements by up to 50%. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks,
%U https://aclanthology.org/2024.mrl-1.11
%P 159-166

Markdown (Informal)

[Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever](https://aclanthology.org/2024.mrl-1.11) (Xiao et al., MRL 2024)

• Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever (Xiao et al., MRL 2024)

ACL

• Han Xiao, Bo Wang, and Rohan Jha. 2024. Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 159–166, Miami, Florida, USA. Association for Computational Linguistics.