@inproceedings{suzgun-etal-2023-follow,
title = "Follow the Wisdom of the Crowd: Effective Text Generation via Minimum {B}ayes Risk Decoding",
author = "Suzgun, Mirac and
Melas-Kyriazi, Luke and
Jurafsky, Dan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.262",
doi = "10.18653/v1/2023.findings-acl.262",
pages = "4265--4293",
abstract = "In open-ended natural-language generation, existing text decoding methods typically struggle to produce text which is both diverse and high-quality. Greedy and beam search are known to suffer from text degeneration and linguistic diversity issues, while temperature, top-k, and nucleus sampling yield diverse but often lower-quality outputs. In this work, we build upon Minimum Bayes Risk Decoding (MBRD), a family of decoding methods based on Bayesian risk minimization, to address this diversity-quality trade-off. Inspired by the principle of the wisdom of the crowd, MBRD seeks to select a candidate from a pool of candidates that has the least expected risk under a generative model according to a given utility function. The crowd of candidates serves as an approximation for the distribution over human-generated references. We show that MBRD generalizes numerous decoding methods, including majority voting, and can be used as a drop-in replacement for existing sampling methods. Across a wide range of tasks{---}such as summarization, data-to-text, translation, and textual style transfer{---}MBRD yields 3-7 ROUGE and BLEU point improvements, including state-of-the-art results on WebNLG and WMT{'}16.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suzgun-etal-2023-follow">
<titleInfo>
<title>Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirac</namePart>
<namePart type="family">Suzgun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Melas-Kyriazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</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>Findings of the Association for Computational Linguistics: ACL 2023</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>In open-ended natural-language generation, existing text decoding methods typically struggle to produce text which is both diverse and high-quality. Greedy and beam search are known to suffer from text degeneration and linguistic diversity issues, while temperature, top-k, and nucleus sampling yield diverse but often lower-quality outputs. In this work, we build upon Minimum Bayes Risk Decoding (MBRD), a family of decoding methods based on Bayesian risk minimization, to address this diversity-quality trade-off. Inspired by the principle of the wisdom of the crowd, MBRD seeks to select a candidate from a pool of candidates that has the least expected risk under a generative model according to a given utility function. The crowd of candidates serves as an approximation for the distribution over human-generated references. We show that MBRD generalizes numerous decoding methods, including majority voting, and can be used as a drop-in replacement for existing sampling methods. Across a wide range of tasks—such as summarization, data-to-text, translation, and textual style transfer—MBRD yields 3-7 ROUGE and BLEU point improvements, including state-of-the-art results on WebNLG and WMT’16.</abstract>
<identifier type="citekey">suzgun-etal-2023-follow</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.262</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.262</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4265</start>
<end>4293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding
%A Suzgun, Mirac
%A Melas-Kyriazi, Luke
%A Jurafsky, Dan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F suzgun-etal-2023-follow
%X In open-ended natural-language generation, existing text decoding methods typically struggle to produce text which is both diverse and high-quality. Greedy and beam search are known to suffer from text degeneration and linguistic diversity issues, while temperature, top-k, and nucleus sampling yield diverse but often lower-quality outputs. In this work, we build upon Minimum Bayes Risk Decoding (MBRD), a family of decoding methods based on Bayesian risk minimization, to address this diversity-quality trade-off. Inspired by the principle of the wisdom of the crowd, MBRD seeks to select a candidate from a pool of candidates that has the least expected risk under a generative model according to a given utility function. The crowd of candidates serves as an approximation for the distribution over human-generated references. We show that MBRD generalizes numerous decoding methods, including majority voting, and can be used as a drop-in replacement for existing sampling methods. Across a wide range of tasks—such as summarization, data-to-text, translation, and textual style transfer—MBRD yields 3-7 ROUGE and BLEU point improvements, including state-of-the-art results on WebNLG and WMT’16.
%R 10.18653/v1/2023.findings-acl.262
%U https://aclanthology.org/2023.findings-acl.262
%U https://doi.org/10.18653/v1/2023.findings-acl.262
%P 4265-4293
Markdown (Informal)
[Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding](https://aclanthology.org/2023.findings-acl.262) (Suzgun et al., Findings 2023)
ACL