<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fried-klein-2018-policy">
    <titleInfo>
        <title>Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Fried</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Klein</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iryna</namePart>
            <namePart type="family">Gurevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yusuke</namePart>
            <namePart type="family">Miyao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Melbourne, Australia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser‘s transition system. We explore using a policy gradient method as a parser-agnostic alternative. In addition to directly optimizing for a tree-level metric such as F1, policy gradient has the potential to reduce exposure bias by allowing exploration during training; moreover, it does not require a dynamic oracle for supervision. On four constituency parsers in three languages, the method substantially outperforms static oracle likelihood training in almost all settings. For parsers where a dynamic oracle is available (including a novel oracle which we define for the transition system of Dyer et al., 2016), policy gradient typically recaptures a substantial fraction of the performance gain afforded by the dynamic oracle.</abstract>
    <identifier type="citekey">fried-klein-2018-policy</identifier>
    <identifier type="doi">10.18653/v1/P18-2075</identifier>
    <location>
        <url>https://aclanthology.org/P18-2075/</url>
    </location>
    <part>
        <date>2018-07</date>
        <extent unit="page">
            <start>469</start>
            <end>476</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing
%A Fried, Daniel
%A Klein, Dan
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F fried-klein-2018-policy
%X Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser‘s transition system. We explore using a policy gradient method as a parser-agnostic alternative. In addition to directly optimizing for a tree-level metric such as F1, policy gradient has the potential to reduce exposure bias by allowing exploration during training; moreover, it does not require a dynamic oracle for supervision. On four constituency parsers in three languages, the method substantially outperforms static oracle likelihood training in almost all settings. For parsers where a dynamic oracle is available (including a novel oracle which we define for the transition system of Dyer et al., 2016), policy gradient typically recaptures a substantial fraction of the performance gain afforded by the dynamic oracle.
%R 10.18653/v1/P18-2075
%U https://aclanthology.org/P18-2075/
%U https://doi.org/10.18653/v1/P18-2075
%P 469-476

Markdown (Informal)

[Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing](https://aclanthology.org/P18-2075/) (Fried & Klein, ACL 2018)

• Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing (Fried & Klein, ACL 2018)

ACL

• Daniel Fried and Dan Klein. 2018. Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 469–476, Melbourne, Australia. Association for Computational Linguistics.