<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="corro-2023-inconsistency">
    <titleInfo>
        <title>On the inconsistency of separable losses for structured prediction</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>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we prove that separable negative log-likelihood losses for structured prediction are not necessarily Bayes consistent, that is minimizing these losses may not result in a model that predicts the most probable structure in the data distribution for a given input. This fact opens the question of whether these losses are well-adapted for structured prediction and, if so, why.</abstract>
    <identifier type="citekey">corro-2023-inconsistency</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.109</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.109</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1491</start>
            <end>1498</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the inconsistency of separable losses for structured prediction
%A Corro, Caio
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F corro-2023-inconsistency
%X In this paper, we prove that separable negative log-likelihood losses for structured prediction are not necessarily Bayes consistent, that is minimizing these losses may not result in a model that predicts the most probable structure in the data distribution for a given input. This fact opens the question of whether these losses are well-adapted for structured prediction and, if so, why.
%R 10.18653/v1/2023.eacl-main.109
%U https://aclanthology.org/2023.eacl-main.109
%U https://doi.org/10.18653/v1/2023.eacl-main.109
%P 1491-1498

Markdown (Informal)

[On the inconsistency of separable losses for structured prediction](https://aclanthology.org/2023.eacl-main.109) (Corro, EACL 2023)

• On the inconsistency of separable losses for structured prediction (Corro, EACL 2023)

ACL

• Caio Corro. 2023. On the inconsistency of separable losses for structured prediction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1491–1498, Dubrovnik, Croatia. Association for Computational Linguistics.