mbrs: A Library for Minimum Bayes Risk Decoding

mbrs: A Library for Minimum Bayes Risk Decoding

Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitabl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Deguchi, Hiroyuki, Sakai, Yusuke, Kamigaito, Hidetaka, Watanabe, Taro
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computation and Language
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Deguchi, Hiroyuki
Sakai, Yusuke
Kamigaito, Hidetaka
Watanabe, Taro
description Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub. GitHub: https://github.com/naist-nlp/mbrs
doi_str_mv 10.48550/arxiv.2408.04167
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2408_04167</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2408_04167</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2408_041673</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjGw0DMwMTQz52TQz00qKrZScFTwyUwqSiyqVEjLL1LwzczLzC3NVXBKrEwtVgjKLM5WcElNzk_JzEvnYWBNS8wpTuWF0twM8m6uIc4eumCj4wuKMnOBpsSDrIgHW2FMWAUAo9IvdA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>mbrs: A Library for Minimum Bayes Risk Decoding</title><source>arXiv.org</source><creator>Deguchi, Hiroyuki ; Sakai, Yusuke ; Kamigaito, Hidetaka ; Watanabe, Taro</creator><creatorcontrib>Deguchi, Hiroyuki ; Sakai, Yusuke ; Kamigaito, Hidetaka ; Watanabe, Taro</creatorcontrib><description>Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub. GitHub: https://github.com/naist-nlp/mbrs</description><identifier>DOI: 10.48550/arxiv.2408.04167</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2024-08</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2408.04167$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2408.04167$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Deguchi, Hiroyuki</creatorcontrib><creatorcontrib>Sakai, Yusuke</creatorcontrib><creatorcontrib>Kamigaito, Hidetaka</creatorcontrib><creatorcontrib>Watanabe, Taro</creatorcontrib><title>mbrs: A Library for Minimum Bayes Risk Decoding</title><description>Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub. GitHub: https://github.com/naist-nlp/mbrs</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjGw0DMwMTQz52TQz00qKrZScFTwyUwqSiyqVEjLL1LwzczLzC3NVXBKrEwtVgjKLM5WcElNzk_JzEvnYWBNS8wpTuWF0twM8m6uIc4eumCj4wuKMnOBpsSDrIgHW2FMWAUAo9IvdA</recordid><startdate>20240807</startdate><enddate>20240807</enddate><creator>Deguchi, Hiroyuki</creator><creator>Sakai, Yusuke</creator><creator>Kamigaito, Hidetaka</creator><creator>Watanabe, Taro</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240807</creationdate><title>mbrs: A Library for Minimum Bayes Risk Decoding</title><author>Deguchi, Hiroyuki ; Sakai, Yusuke ; Kamigaito, Hidetaka ; Watanabe, Taro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2408_041673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Deguchi, Hiroyuki</creatorcontrib><creatorcontrib>Sakai, Yusuke</creatorcontrib><creatorcontrib>Kamigaito, Hidetaka</creatorcontrib><creatorcontrib>Watanabe, Taro</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Deguchi, Hiroyuki</au><au>Sakai, Yusuke</au><au>Kamigaito, Hidetaka</au><au>Watanabe, Taro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>mbrs: A Library for Minimum Bayes Risk Decoding</atitle><date>2024-08-07</date><risdate>2024</risdate><abstract>Minimum Bayes risk (MBR) decoding is a decision rule of text generation tasks that outperforms conventional maximum a posterior (MAP) decoding using beam search by selecting high-quality outputs based on a utility function rather than those with high-probability. Typically, it finds the most suitable hypothesis from the set of hypotheses under the sampled pseudo-references. mbrs is a library of MBR decoding, which can flexibly combine various metrics, alternative expectation estimations, and algorithmic variants. It is designed with a focus on speed measurement and calling count of code blocks, transparency, reproducibility, and extensibility, which are essential for researchers and developers. We published our mbrs as an MIT-licensed open-source project, and the code is available on GitHub. GitHub: https://github.com/naist-nlp/mbrs</abstract><doi>10.48550/arxiv.2408.04167</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2408.04167
ispartof
issn
language eng
recordid cdi_arxiv_primary_2408_04167
source arXiv.org
subjects Computer Science - Computation and Language
title mbrs: A Library for Minimum Bayes Risk Decoding
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T03%3A48%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=mbrs:%20A%20Library%20for%20Minimum%20Bayes%20Risk%20Decoding&rft.au=Deguchi,%20Hiroyuki&rft.date=2024-08-07&rft_id=info:doi/10.48550/arxiv.2408.04167&rft_dat=%3Carxiv_GOX%3E2408_04167%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true