<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2023-maggretriever">
    <titleInfo>
        <title>mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sheng-Chieh</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amin</namePart>
        <namePart type="family">Ahmad</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>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Multilingual information retrieval (MLIR) is a crucial yet challenging task due to the need for human annotations in multiple languages, making training data creation labor-intensive. In this paper, we introduce mAggretriever, which effectively leverages semantic and lexical features from pre-trained multilingual transformers (e.g., mBERT and XLM-R) for dense retrieval. To enhance training and inference efficiency, we employ approximate masked-language modeling prediction for computing lexical features, reducing 70–85% GPU memory requirement for mAggretriever fine-tuning. Empirical results demonstrate that mAggretriever, fine-tuned solely on English training data, surpasses existing state-of-the-art multilingual dense retrieval models that undergo further training on large-scale MLIR training data. Our code is available at url.</abstract>
    <identifier type="citekey">lin-etal-2023-maggretriever</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.715</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.715/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>11688</start>
            <end>11696</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval
%A Lin, Sheng-Chieh
%A Ahmad, Amin
%A Lin, Jimmy
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lin-etal-2023-maggretriever
%X Multilingual information retrieval (MLIR) is a crucial yet challenging task due to the need for human annotations in multiple languages, making training data creation labor-intensive. In this paper, we introduce mAggretriever, which effectively leverages semantic and lexical features from pre-trained multilingual transformers (e.g., mBERT and XLM-R) for dense retrieval. To enhance training and inference efficiency, we employ approximate masked-language modeling prediction for computing lexical features, reducing 70–85% GPU memory requirement for mAggretriever fine-tuning. Empirical results demonstrate that mAggretriever, fine-tuned solely on English training data, surpasses existing state-of-the-art multilingual dense retrieval models that undergo further training on large-scale MLIR training data. Our code is available at url.
%R 10.18653/v1/2023.emnlp-main.715
%U https://aclanthology.org/2023.emnlp-main.715/
%U https://doi.org/10.18653/v1/2023.emnlp-main.715
%P 11688-11696

Markdown (Informal)

[mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval](https://aclanthology.org/2023.emnlp-main.715/) (Lin et al., EMNLP 2023)

• mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval (Lin et al., EMNLP 2023)

ACL

• Sheng-Chieh Lin, Amin Ahmad, and Jimmy Lin. 2023. mAggretriever: A Simple yet Effective Approach to Zero-Shot Multilingual Dense Retrieval. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11688–11696, Singapore. Association for Computational Linguistics.