<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dary-etal-2022-dependency">
    <titleInfo>
        <title>Dependency Parsing with Backtracking using Deep Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Franck</namePart>
        <namePart type="family">Dary</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maxime</namePart>
        <namePart type="family">Petit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexis</namePart>
        <namePart type="family">Nasr</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Greedy algorithms for NLP such as transition-based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new evidence contradicts the solution explored so far. In order to implement such a behavior, we use reinforcement learning and let the algorithm backtrack in cases where such an action gets a better reward than continuing to explore the current solution. We test this idea on both POS tagging and dependency parsing and show that backtracking is an effective means to fight against error propagation.</abstract>
    <identifier type="citekey">dary-etal-2022-dependency</identifier>
    <identifier type="doi">10.1162/tacl_a_00496</identifier>
    <location>
        <url>https://aclanthology.org/2022.tacl-1.52</url>
    </location>
    <part>
        <date>2022</date>
        <detail type="volume"><number>10</number></detail>
        <extent unit="page">
            <start>888</start>
            <end>903</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Dependency Parsing with Backtracking using Deep Reinforcement Learning
%A Dary, Franck
%A Petit, Maxime
%A Nasr, Alexis
%J Transactions of the Association for Computational Linguistics
%D 2022
%V 10
%I MIT Press
%C Cambridge, MA
%F dary-etal-2022-dependency
%X Greedy algorithms for NLP such as transition-based parsing are prone to error propagation. One way to overcome this problem is to allow the algorithm to backtrack and explore an alternative solution in cases where new evidence contradicts the solution explored so far. In order to implement such a behavior, we use reinforcement learning and let the algorithm backtrack in cases where such an action gets a better reward than continuing to explore the current solution. We test this idea on both POS tagging and dependency parsing and show that backtracking is an effective means to fight against error propagation.
%R 10.1162/tacl_a_00496
%U https://aclanthology.org/2022.tacl-1.52
%U https://doi.org/10.1162/tacl_a_00496
%P 888-903

Markdown (Informal)

[Dependency Parsing with Backtracking using Deep Reinforcement Learning](https://aclanthology.org/2022.tacl-1.52) (Dary et al., TACL 2022)

• Dependency Parsing with Backtracking using Deep Reinforcement Learning (Dary et al., TACL 2022)

ACL

• Franck Dary, Maxime Petit, and Alexis Nasr. 2022. Dependency Parsing with Backtracking using Deep Reinforcement Learning. Transactions of the Association for Computational Linguistics, 10:888–903.