<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hemmer-etal-2023-lazy">
    <titleInfo>
        <title>Lazy-k Decoding: Constrained Decoding for Information Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Arthur</namePart>
        <namePart type="family">Hemmer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mickael</namePart>
        <namePart type="family">Coustaty</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicola</namePart>
        <namePart type="family">Bartolo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jerome</namePart>
        <namePart type="family">Brachat</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jean-marc</namePart>
        <namePart type="family">Ogier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-k. Our findings demonstrate that constrained decoding approaches can significantly improve the models’ performances, especially when using smaller models. The Lazy-k approach allows for more flexibility between decoding time and accuracy. The code for using Lazy-k decoding can be found at https://github.com/ArthurDevNL/lazyk.</abstract>
    <identifier type="citekey">hemmer-etal-2023-lazy</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.416</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.416</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>6727</start>
            <end>6736</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lazy-k Decoding: Constrained Decoding for Information Extraction
%A Hemmer, Arthur
%A Coustaty, Mickael
%A Bartolo, Nicola
%A Brachat, Jerome
%A Ogier, Jean-marc
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F hemmer-etal-2023-lazy
%X We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-k. Our findings demonstrate that constrained decoding approaches can significantly improve the models’ performances, especially when using smaller models. The Lazy-k approach allows for more flexibility between decoding time and accuracy. The code for using Lazy-k decoding can be found at https://github.com/ArthurDevNL/lazyk.
%R 10.18653/v1/2023.emnlp-main.416
%U https://aclanthology.org/2023.emnlp-main.416
%U https://doi.org/10.18653/v1/2023.emnlp-main.416
%P 6727-6736

Markdown (Informal)

[Lazy-k Decoding: Constrained Decoding for Information Extraction](https://aclanthology.org/2023.emnlp-main.416) (Hemmer et al., EMNLP 2023)

• Lazy-k Decoding: Constrained Decoding for Information Extraction (Hemmer et al., EMNLP 2023)

ACL

• Arthur Hemmer, Mickael Coustaty, Nicola Bartolo, Jerome Brachat, and Jean-marc Ogier. 2023. Lazy-k Decoding: Constrained Decoding for Information Extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6727–6736, Singapore. Association for Computational Linguistics.