<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kreutzer-etal-2017-bandit">
    <titleInfo>
        <title>Bandit Structured Prediction for Neural Sequence-to-Sequence Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Julia</namePart>
        <namePart type="family">Kreutzer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Artem</namePart>
        <namePart type="family">Sokolov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stefan</namePart>
        <namePart type="family">Riezler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks. Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization. We present an evaluation on a neural machine translation task that shows improvements of up to 5.89 BLEU points for domain adaptation from simulated bandit feedback.</abstract>
    <identifier type="citekey">kreutzer-etal-2017-bandit</identifier>
    <identifier type="doi">10.18653/v1/P17-1138</identifier>
    <location>
        <url>https://aclanthology.org/P17-1138</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>1503</start>
            <end>1513</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
%A Kreutzer, Julia
%A Sokolov, Artem
%A Riezler, Stefan
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F kreutzer-etal-2017-bandit
%X Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks. Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization. We present an evaluation on a neural machine translation task that shows improvements of up to 5.89 BLEU points for domain adaptation from simulated bandit feedback.
%R 10.18653/v1/P17-1138
%U https://aclanthology.org/P17-1138
%U https://doi.org/10.18653/v1/P17-1138
%P 1503-1513

Markdown (Informal)

[Bandit Structured Prediction for Neural Sequence-to-Sequence Learning](https://aclanthology.org/P17-1138) (Kreutzer et al., ACL 2017)

• Bandit Structured Prediction for Neural Sequence-to-Sequence Learning (Kreutzer et al., ACL 2017)

ACL

• Julia Kreutzer, Artem Sokolov, and Stefan Riezler. 2017. Bandit Structured Prediction for Neural Sequence-to-Sequence Learning. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1503–1513, Vancouver, Canada. Association for Computational Linguistics.