<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garmash-monz-2016-ensemble">
    <titleInfo>
        <title>Ensemble Learning for Multi-Source Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ekaterina</namePart>
        <namePart type="family">Garmash</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yuji</namePart>
            <namePart type="family">Matsumoto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rashmi</namePart>
            <namePart type="family">Prasad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper we describe and evaluate methods to perform ensemble prediction in neural machine translation (NMT). We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i.e., multi-source ensembles, a method recently introduced by Firat et al. (2016). We are motivated by the observation that for different language pairs systems make different types of mistakes. We propose several methods with different degrees of parameterization to combine individual predictions of NMT systems so that they mutually compensate for each other’s mistakes and improve overall performance. We find that the biggest improvements can be obtained from a context-dependent weighting scheme for multi-source ensembles. This result offers stronger support for the linguistic motivation of using multi-source ensembles than previous approaches. Evaluation is carried out for German and French into English translation. The best multi-source ensemble method achieves an improvement of up to 2.2 BLEU points over the strongest single-source ensemble baseline, and a 2 BLEU improvement over a multi-source ensemble baseline.</abstract>
    <identifier type="citekey">garmash-monz-2016-ensemble</identifier>
    <location>
        <url>https://aclanthology.org/C16-1133</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>1409</start>
            <end>1418</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Ensemble Learning for Multi-Source Neural Machine Translation
%A Garmash, Ekaterina
%A Monz, Christof
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F garmash-monz-2016-ensemble
%X In this paper we describe and evaluate methods to perform ensemble prediction in neural machine translation (NMT). We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i.e., multi-source ensembles, a method recently introduced by Firat et al. (2016). We are motivated by the observation that for different language pairs systems make different types of mistakes. We propose several methods with different degrees of parameterization to combine individual predictions of NMT systems so that they mutually compensate for each other’s mistakes and improve overall performance. We find that the biggest improvements can be obtained from a context-dependent weighting scheme for multi-source ensembles. This result offers stronger support for the linguistic motivation of using multi-source ensembles than previous approaches. Evaluation is carried out for German and French into English translation. The best multi-source ensemble method achieves an improvement of up to 2.2 BLEU points over the strongest single-source ensemble baseline, and a 2 BLEU improvement over a multi-source ensemble baseline.
%U https://aclanthology.org/C16-1133
%P 1409-1418

Markdown (Informal)

[Ensemble Learning for Multi-Source Neural Machine Translation](https://aclanthology.org/C16-1133) (Garmash & Monz, COLING 2016)

• Ensemble Learning for Multi-Source Neural Machine Translation (Garmash & Monz, COLING 2016)

ACL

• Ekaterina Garmash and Christof Monz. 2016. Ensemble Learning for Multi-Source Neural Machine Translation. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1409–1418, Osaka, Japan. The COLING 2016 Organizing Committee.