@inproceedings{deguchi-etal-2024-centroid,
title = "Centroid-Based Efficient Minimum {B}ayes Risk Decoding",
author = "Deguchi, Hiroyuki and
Sakai, Yusuke and
Kamigaito, Hidetaka and
Watanabe, Taro and
Tanaka, Hideki and
Utiyama, Masao",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.654",
doi = "10.18653/v1/2024.findings-acl.654",
pages = "11009--11018",
abstract = "Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.However, MBR decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations.We propose centroid-based MBR (CBMBR) decoding to improve the speed of MBR decoding.Our method clusters the reference translations in the feature space, and then calculates the score using the centroids of each cluster.The experimental results show that our CBMBR not only improved the decoding speed of the expected score calculation 5.7 times, but also outperformed vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT{'}22 En$\leftrightarrow$Ja, En$\leftrightarrow$De, En$\leftrightarrow$Zh, and WMT{'}23 En$\leftrightarrow$Ja translation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deguchi-etal-2024-centroid">
<titleInfo>
<title>Centroid-Based Efficient Minimum Bayes Risk Decoding</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">Yusuke</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hidetaka</namePart>
<namePart type="family">Kamigaito</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">Hideki</namePart>
<namePart type="family">Tanaka</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>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.However, MBR decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations.We propose centroid-based MBR (CBMBR) decoding to improve the speed of MBR decoding.Our method clusters the reference translations in the feature space, and then calculates the score using the centroids of each cluster.The experimental results show that our CBMBR not only improved the decoding speed of the expected score calculation 5.7 times, but also outperformed vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT’22 EnłeftrightarrowJa, EnłeftrightarrowDe, EnłeftrightarrowZh, and WMT’23 EnłeftrightarrowJa translation tasks.</abstract>
<identifier type="citekey">deguchi-etal-2024-centroid</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.654</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.654</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11009</start>
<end>11018</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Centroid-Based Efficient Minimum Bayes Risk Decoding
%A Deguchi, Hiroyuki
%A Sakai, Yusuke
%A Kamigaito, Hidetaka
%A Watanabe, Taro
%A Tanaka, Hideki
%A Utiyama, Masao
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F deguchi-etal-2024-centroid
%X Minimum Bayes risk (MBR) decoding achieved state-of-the-art translation performance by using COMET, a neural metric that has a high correlation with human evaluation.However, MBR decoding requires quadratic time since it computes the expected score between a translation hypothesis and all reference translations.We propose centroid-based MBR (CBMBR) decoding to improve the speed of MBR decoding.Our method clusters the reference translations in the feature space, and then calculates the score using the centroids of each cluster.The experimental results show that our CBMBR not only improved the decoding speed of the expected score calculation 5.7 times, but also outperformed vanilla MBR decoding in translation quality by up to 0.5 COMET in the WMT’22 EnłeftrightarrowJa, EnłeftrightarrowDe, EnłeftrightarrowZh, and WMT’23 EnłeftrightarrowJa translation tasks.
%R 10.18653/v1/2024.findings-acl.654
%U https://aclanthology.org/2024.findings-acl.654
%U https://doi.org/10.18653/v1/2024.findings-acl.654
%P 11009-11018
Markdown (Informal)
[Centroid-Based Efficient Minimum Bayes Risk Decoding](https://aclanthology.org/2024.findings-acl.654) (Deguchi et al., Findings 2024)
ACL
- Hiroyuki Deguchi, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe, Hideki Tanaka, and Masao Utiyama. 2024. Centroid-Based Efficient Minimum Bayes Risk Decoding. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11009–11018, Bangkok, Thailand. Association for Computational Linguistics.