@inproceedings{corro-etal-2025-bregman,
title = "Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms",
author = "Corro, Caio and
Lacroix, Mathieu and
Roux, Joseph Le",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1430/",
doi = "10.18653/v1/2025.acl-long.1430",
pages = "29557--29574",
ISBN = "979-8-89176-251-0",
abstract = "We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF).Contrary to standard linear-chain conditional random fields,BCRF allows fast parallelizable inference algorithms based on iterative Bregman projections.We show how such models can be learned using Fenchel-Young losses, including extension for learning from partial labels.Experimentally, our approach delivers comparable results to CRF while being faster, and achieves better results in highly constrained settings compared to mean field, another parallelizable alternative."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="corro-etal-2025-bregman">
<titleInfo>
<title>Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Caio</namePart>
<namePart type="family">Corro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Lacroix</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">Le</namePart>
<namePart type="family">Roux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF).Contrary to standard linear-chain conditional random fields,BCRF allows fast parallelizable inference algorithms based on iterative Bregman projections.We show how such models can be learned using Fenchel-Young losses, including extension for learning from partial labels.Experimentally, our approach delivers comparable results to CRF while being faster, and achieves better results in highly constrained settings compared to mean field, another parallelizable alternative.</abstract>
<identifier type="citekey">corro-etal-2025-bregman</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1430</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1430/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>29557</start>
<end>29574</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms
%A Corro, Caio
%A Lacroix, Mathieu
%A Roux, Joseph Le
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F corro-etal-2025-bregman
%X We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF).Contrary to standard linear-chain conditional random fields,BCRF allows fast parallelizable inference algorithms based on iterative Bregman projections.We show how such models can be learned using Fenchel-Young losses, including extension for learning from partial labels.Experimentally, our approach delivers comparable results to CRF while being faster, and achieves better results in highly constrained settings compared to mean field, another parallelizable alternative.
%R 10.18653/v1/2025.acl-long.1430
%U https://aclanthology.org/2025.acl-long.1430/
%U https://doi.org/10.18653/v1/2025.acl-long.1430
%P 29557-29574
Markdown (Informal)
[Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms](https://aclanthology.org/2025.acl-long.1430/) (Corro et al., ACL 2025)
ACL