@inproceedings{deguchi-etal-2023-subset,
title = "Subset Retrieval Nearest Neighbor Machine Translation",
author = "Deguchi, Hiroyuki and
Watanabe, Taro and
Matsui, Yusuke and
Utiyama, Masao and
Tanaka, Hideki and
Sumita, Eiichiro",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.10",
doi = "10.18653/v1/2023.acl-long.10",
pages = "174--189",
abstract = "k-nearest-neighbor machine translation (kNN-MT) (Khandelwal et al., 2021) boosts the translation performance of trained neural machine translation (NMT) models by incorporating example-search into the decoding algorithm. However, decoding is seriously time-consuming, i.e., roughly 100 to 1,000 times slower than standard NMT, because neighbor tokens are retrieved from all target tokens of parallel data in each timestep. In this paper, we propose {``}Subset kNN-MT{''}, which improves the decoding speed of kNN-MT by two methods: (1) retrieving neighbor target tokens from a subset that is the set of neighbor sentences of the input sentence, not from all sentences, and (2) efficient distance computation technique that is suitable for subset neighbor search using a look-up table. Our proposed method achieved a speed-up of up to 132.2 times and an improvement in BLEU score of up to 1.6 compared with kNN-MT in the WMT{'}19 De-En translation task and the domain adaptation tasks in De-En and En-Ja.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deguchi-etal-2023-subset">
<titleInfo>
<title>Subset Retrieval Nearest Neighbor Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hiroyuki</namePart>
<namePart type="family">Deguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Matsui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Tanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>k-nearest-neighbor machine translation (kNN-MT) (Khandelwal et al., 2021) boosts the translation performance of trained neural machine translation (NMT) models by incorporating example-search into the decoding algorithm. However, decoding is seriously time-consuming, i.e., roughly 100 to 1,000 times slower than standard NMT, because neighbor tokens are retrieved from all target tokens of parallel data in each timestep. In this paper, we propose “Subset kNN-MT”, which improves the decoding speed of kNN-MT by two methods: (1) retrieving neighbor target tokens from a subset that is the set of neighbor sentences of the input sentence, not from all sentences, and (2) efficient distance computation technique that is suitable for subset neighbor search using a look-up table. Our proposed method achieved a speed-up of up to 132.2 times and an improvement in BLEU score of up to 1.6 compared with kNN-MT in the WMT’19 De-En translation task and the domain adaptation tasks in De-En and En-Ja.</abstract>
<identifier type="citekey">deguchi-etal-2023-subset</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.10</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.10</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>174</start>
<end>189</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subset Retrieval Nearest Neighbor Machine Translation
%A Deguchi, Hiroyuki
%A Watanabe, Taro
%A Matsui, Yusuke
%A Utiyama, Masao
%A Tanaka, Hideki
%A Sumita, Eiichiro
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F deguchi-etal-2023-subset
%X k-nearest-neighbor machine translation (kNN-MT) (Khandelwal et al., 2021) boosts the translation performance of trained neural machine translation (NMT) models by incorporating example-search into the decoding algorithm. However, decoding is seriously time-consuming, i.e., roughly 100 to 1,000 times slower than standard NMT, because neighbor tokens are retrieved from all target tokens of parallel data in each timestep. In this paper, we propose “Subset kNN-MT”, which improves the decoding speed of kNN-MT by two methods: (1) retrieving neighbor target tokens from a subset that is the set of neighbor sentences of the input sentence, not from all sentences, and (2) efficient distance computation technique that is suitable for subset neighbor search using a look-up table. Our proposed method achieved a speed-up of up to 132.2 times and an improvement in BLEU score of up to 1.6 compared with kNN-MT in the WMT’19 De-En translation task and the domain adaptation tasks in De-En and En-Ja.
%R 10.18653/v1/2023.acl-long.10
%U https://aclanthology.org/2023.acl-long.10
%U https://doi.org/10.18653/v1/2023.acl-long.10
%P 174-189
Markdown (Informal)
[Subset Retrieval Nearest Neighbor Machine Translation](https://aclanthology.org/2023.acl-long.10) (Deguchi et al., ACL 2023)
ACL
- Hiroyuki Deguchi, Taro Watanabe, Yusuke Matsui, Masao Utiyama, Hideki Tanaka, and Eiichiro Sumita. 2023. Subset Retrieval Nearest Neighbor Machine Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 174–189, Toronto, Canada. Association for Computational Linguistics.