<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stap-monz-2023-multilingual">
    <titleInfo>
        <title>Multilingual k-Nearest-Neighbor Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">David</namePart>
        <namePart type="family">Stap</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</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>k-nearest-neighbor machine translation has demonstrated remarkable improvements in machine translation quality by creating a datastore of cached examples. However, these improvements have been limited to high-resource language pairs, with large datastores, and remain a challenge for low-resource languages. In this paper, we address this issue by combining representations from multiple languages into a single datastore. Our results consistently demonstrate substantial improvements not only in low-resource translation quality (up to +3.6 BLEU), but also for high-resource translation quality (up to +0.5 BLEU). Our experiments show that it is possible to create multilingual datastores that are a quarter of the size, achieving a 5.3x speed improvement, by using linguistic similarities for datastore creation.</abstract>
    <identifier type="citekey">stap-monz-2023-multilingual</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.571</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.571/</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>9200</start>
            <end>9208</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multilingual k-Nearest-Neighbor Machine Translation
%A Stap, David
%A Monz, Christof
%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 stap-monz-2023-multilingual
%X k-nearest-neighbor machine translation has demonstrated remarkable improvements in machine translation quality by creating a datastore of cached examples. However, these improvements have been limited to high-resource language pairs, with large datastores, and remain a challenge for low-resource languages. In this paper, we address this issue by combining representations from multiple languages into a single datastore. Our results consistently demonstrate substantial improvements not only in low-resource translation quality (up to +3.6 BLEU), but also for high-resource translation quality (up to +0.5 BLEU). Our experiments show that it is possible to create multilingual datastores that are a quarter of the size, achieving a 5.3x speed improvement, by using linguistic similarities for datastore creation.
%R 10.18653/v1/2023.emnlp-main.571
%U https://aclanthology.org/2023.emnlp-main.571/
%U https://doi.org/10.18653/v1/2023.emnlp-main.571
%P 9200-9208

Markdown (Informal)

[Multilingual k-Nearest-Neighbor Machine Translation](https://aclanthology.org/2023.emnlp-main.571/) (Stap & Monz, EMNLP 2023)

• Multilingual k-Nearest-Neighbor Machine Translation (Stap & Monz, EMNLP 2023)

ACL

• David Stap and Christof Monz. 2023. Multilingual k-Nearest-Neighbor Machine Translation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9200–9208, Singapore. Association for Computational Linguistics.