@inproceedings{ohashi-etal-2024-true,
title = "On the True Distribution Approximation of Minimum {B}ayes-Risk Decoding",
author = "Ohashi, Atsumoto and
Honda, Ukyo and
Morimura, Tetsuro and
Jinnai, Yuu",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.38",
pages = "459--468",
abstract = "Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation.MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others.Therefore, sampling is one of the key elements of MBR decoding, and previous studies reported that the performance varies by sampling methods.From a theoretical standpoint, this performance variation is likely tied to how closely the samples approximate the true distribution of references.However, this approximation has not been the subject of in-depth study.In this study, we propose using anomaly detection to measure the degree of approximation.We first closely examine the performance variation and then show that previous hypotheses about samples do not correlate well with the variation, but our introduced anomaly scores do.The results are the first to empirically support the link between the performance and the core assumption of MBR decoding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ohashi-etal-2024-true">
<titleInfo>
<title>On the True Distribution Approximation of Minimum Bayes-Risk Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atsumoto</namePart>
<namePart type="family">Ohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ukyo</namePart>
<namePart type="family">Honda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuro</namePart>
<namePart type="family">Morimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuu</namePart>
<namePart type="family">Jinnai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation.MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others.Therefore, sampling is one of the key elements of MBR decoding, and previous studies reported that the performance varies by sampling methods.From a theoretical standpoint, this performance variation is likely tied to how closely the samples approximate the true distribution of references.However, this approximation has not been the subject of in-depth study.In this study, we propose using anomaly detection to measure the degree of approximation.We first closely examine the performance variation and then show that previous hypotheses about samples do not correlate well with the variation, but our introduced anomaly scores do.The results are the first to empirically support the link between the performance and the core assumption of MBR decoding.</abstract>
<identifier type="citekey">ohashi-etal-2024-true</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.38</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>459</start>
<end>468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the True Distribution Approximation of Minimum Bayes-Risk Decoding
%A Ohashi, Atsumoto
%A Honda, Ukyo
%A Morimura, Tetsuro
%A Jinnai, Yuu
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F ohashi-etal-2024-true
%X Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation.MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others.Therefore, sampling is one of the key elements of MBR decoding, and previous studies reported that the performance varies by sampling methods.From a theoretical standpoint, this performance variation is likely tied to how closely the samples approximate the true distribution of references.However, this approximation has not been the subject of in-depth study.In this study, we propose using anomaly detection to measure the degree of approximation.We first closely examine the performance variation and then show that previous hypotheses about samples do not correlate well with the variation, but our introduced anomaly scores do.The results are the first to empirically support the link between the performance and the core assumption of MBR decoding.
%U https://aclanthology.org/2024.naacl-short.38
%P 459-468
Markdown (Informal)
[On the True Distribution Approximation of Minimum Bayes-Risk Decoding](https://aclanthology.org/2024.naacl-short.38) (Ohashi et al., NAACL 2024)
ACL
- Atsumoto Ohashi, Ukyo Honda, Tetsuro Morimura, and Yuu Jinnai. 2024. On the True Distribution Approximation of Minimum Bayes-Risk Decoding. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 459–468, Mexico City, Mexico. Association for Computational Linguistics.