<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2018-approximate">
    <titleInfo>
        <title>Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiang</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ngoc</namePart>
        <namePart type="given">Thang</namePart>
        <namePart type="family">Vu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jonas</namePart>
        <namePart type="family">Kuhn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Teresa</namePart>
            <namePart type="family">Lynn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Schuster</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present a general approach with reinforcement learning (RL) to approximate dynamic oracles for transition systems where exact dynamic oracles are difficult to derive. We treat oracle parsing as a reinforcement learning problem, design the reward function inspired by the classical dynamic oracle, and use Deep Q-Learning (DQN) techniques to train the oracle with gold trees as features. The combination of a priori knowledge and data-driven methods enables an efficient dynamic oracle, which improves the parser performance over static oracles in several transition systems.</abstract>
    <identifier type="citekey">yu-etal-2018-approximate</identifier>
    <identifier type="doi">10.18653/v1/W18-6021</identifier>
    <location>
        <url>https://aclanthology.org/W18-6021</url>
    </location>
    <part>
        <date>2018-11</date>
        <extent unit="page">
            <start>183</start>
            <end>191</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning
%A Yu, Xiang
%A Vu, Ngoc Thang
%A Kuhn, Jonas
%Y de Marneffe, Marie-Catherine
%Y Lynn, Teresa
%Y Schuster, Sebastian
%S Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F yu-etal-2018-approximate
%X We present a general approach with reinforcement learning (RL) to approximate dynamic oracles for transition systems where exact dynamic oracles are difficult to derive. We treat oracle parsing as a reinforcement learning problem, design the reward function inspired by the classical dynamic oracle, and use Deep Q-Learning (DQN) techniques to train the oracle with gold trees as features. The combination of a priori knowledge and data-driven methods enables an efficient dynamic oracle, which improves the parser performance over static oracles in several transition systems.
%R 10.18653/v1/W18-6021
%U https://aclanthology.org/W18-6021
%U https://doi.org/10.18653/v1/W18-6021
%P 183-191

Markdown (Informal)

[Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning](https://aclanthology.org/W18-6021) (Yu et al., UDW 2018)

• Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning (Yu et al., UDW 2018)

ACL

• Xiang Yu, Ngoc Thang Vu, and Jonas Kuhn. 2018. Approximate Dynamic Oracle for Dependency Parsing with Reinforcement Learning. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pages 183–191, Brussels, Belgium. Association for Computational Linguistics.