@inproceedings{meng-etal-2022-fast,
title = "Fast Nearest Neighbor Machine Translation",
author = "Meng, Yuxian and
Li, Xiaoya and
Zheng, Xiayu and
Wu, Fei and
Sun, Xiaofei and
Zhang, Tianwei and
Li, Jiwei",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.47",
doi = "10.18653/v1/2022.findings-acl.47",
pages = "555--565",
abstract = "Though nearest neighbor Machine Translation ($k$NN-MT) (CITATION) has proved to introduce significant performance boosts over standard neural MT systems, it is prohibitively slow since it uses the entire reference corpus as the datastore for the nearest neighbor search. This means each step for each beam in the beam search has to search over the entire reference corpus. $k$NN-MT is thus two-orders slower than vanilla MT models, making it hard to be applied to real-world applications, especially online services. In this work, we propose Fast $k$NN-MT to address this issue. Fast $k$NN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast $k$NN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token. Then at each decoding step, in contrast to using the entire corpus as the datastore, the search space is limited to target tokens corresponding to the previously selected reference source tokens. This strategy avoids search through the whole datastore for nearest neighbors and drastically improves decoding efficiency. Without loss of performance, Fast $k$NN-MT is two-orders faster than $k$NN-MT, and is only two times slower than the standard NMT model. Fast $k$NN-MT enables the practical use of $k$NN-MT systems in real-world MT applications. The code is available at \url{https://github.com/ShannonAI/fast-knn-nmt}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meng-etal-2022-fast">
<titleInfo>
<title>Fast Nearest Neighbor Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxian</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoya</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiayu</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianwei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiwei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Though nearest neighbor Machine Translation (kNN-MT) (CITATION) has proved to introduce significant performance boosts over standard neural MT systems, it is prohibitively slow since it uses the entire reference corpus as the datastore for the nearest neighbor search. This means each step for each beam in the beam search has to search over the entire reference corpus. kNN-MT is thus two-orders slower than vanilla MT models, making it hard to be applied to real-world applications, especially online services. In this work, we propose Fast kNN-MT to address this issue. Fast kNN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast kNN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token. Then at each decoding step, in contrast to using the entire corpus as the datastore, the search space is limited to target tokens corresponding to the previously selected reference source tokens. This strategy avoids search through the whole datastore for nearest neighbors and drastically improves decoding efficiency. Without loss of performance, Fast kNN-MT is two-orders faster than kNN-MT, and is only two times slower than the standard NMT model. Fast kNN-MT enables the practical use of kNN-MT systems in real-world MT applications. The code is available at https://github.com/ShannonAI/fast-knn-nmt.</abstract>
<identifier type="citekey">meng-etal-2022-fast</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.47</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.47</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>555</start>
<end>565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fast Nearest Neighbor Machine Translation
%A Meng, Yuxian
%A Li, Xiaoya
%A Zheng, Xiayu
%A Wu, Fei
%A Sun, Xiaofei
%A Zhang, Tianwei
%A Li, Jiwei
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F meng-etal-2022-fast
%X Though nearest neighbor Machine Translation (kNN-MT) (CITATION) has proved to introduce significant performance boosts over standard neural MT systems, it is prohibitively slow since it uses the entire reference corpus as the datastore for the nearest neighbor search. This means each step for each beam in the beam search has to search over the entire reference corpus. kNN-MT is thus two-orders slower than vanilla MT models, making it hard to be applied to real-world applications, especially online services. In this work, we propose Fast kNN-MT to address this issue. Fast kNN-MT constructs a significantly smaller datastore for the nearest neighbor search: for each word in a source sentence, Fast kNN-MT first selects its nearest token-level neighbors, which is limited to tokens that are the same as the query token. Then at each decoding step, in contrast to using the entire corpus as the datastore, the search space is limited to target tokens corresponding to the previously selected reference source tokens. This strategy avoids search through the whole datastore for nearest neighbors and drastically improves decoding efficiency. Without loss of performance, Fast kNN-MT is two-orders faster than kNN-MT, and is only two times slower than the standard NMT model. Fast kNN-MT enables the practical use of kNN-MT systems in real-world MT applications. The code is available at https://github.com/ShannonAI/fast-knn-nmt.
%R 10.18653/v1/2022.findings-acl.47
%U https://aclanthology.org/2022.findings-acl.47
%U https://doi.org/10.18653/v1/2022.findings-acl.47
%P 555-565
Markdown (Informal)
[Fast Nearest Neighbor Machine Translation](https://aclanthology.org/2022.findings-acl.47) (Meng et al., Findings 2022)
ACL
- Yuxian Meng, Xiaoya Li, Xiayu Zheng, Fei Wu, Xiaofei Sun, Tianwei Zhang, and Jiwei Li. 2022. Fast Nearest Neighbor Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 555–565, Dublin, Ireland. Association for Computational Linguistics.