<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-der-wees-etal-2017-dynamic">
    <titleInfo>
        <title>Dynamic Data Selection for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marlies</namePart>
        <namePart type="family">van der Wees</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Arianna</namePart>
        <namePart type="family">Bisazza</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>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of neural machine translation (NMT), we explore in this paper to what extent and how NMT can also benefit from data selection. While state-of-the-art data selection (Axelrod et al., 2011) consistently performs well for PBMT, we show that gains are substantially lower for NMT. Next, we introduce ‘dynamic data selection’ for NMT, a method in which we vary the selected subset of training data between different training epochs. Our experiments show that the best results are achieved when applying a technique we call ‘gradual fine-tuning’, with improvements up to +2.6 BLEU over the original data selection approach and up to +3.1 BLEU over a general baseline.</abstract>
    <identifier type="citekey">van-der-wees-etal-2017-dynamic</identifier>
    <identifier type="doi">10.18653/v1/D17-1147</identifier>
    <location>
        <url>https://aclanthology.org/D17-1147</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>1400</start>
            <end>1410</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Dynamic Data Selection for Neural Machine Translation
%A van der Wees, Marlies
%A Bisazza, Arianna
%A Monz, Christof
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F van-der-wees-etal-2017-dynamic
%X Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of neural machine translation (NMT), we explore in this paper to what extent and how NMT can also benefit from data selection. While state-of-the-art data selection (Axelrod et al., 2011) consistently performs well for PBMT, we show that gains are substantially lower for NMT. Next, we introduce ‘dynamic data selection’ for NMT, a method in which we vary the selected subset of training data between different training epochs. Our experiments show that the best results are achieved when applying a technique we call ‘gradual fine-tuning’, with improvements up to +2.6 BLEU over the original data selection approach and up to +3.1 BLEU over a general baseline.
%R 10.18653/v1/D17-1147
%U https://aclanthology.org/D17-1147
%U https://doi.org/10.18653/v1/D17-1147
%P 1400-1410

Markdown (Informal)

[Dynamic Data Selection for Neural Machine Translation](https://aclanthology.org/D17-1147) (van der Wees et al., EMNLP 2017)

• Dynamic Data Selection for Neural Machine Translation (van der Wees et al., EMNLP 2017)

ACL

• Marlies van der Wees, Arianna Bisazza, and Christof Monz. 2017. Dynamic Data Selection for Neural Machine Translation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1400–1410, Copenhagen, Denmark. Association for Computational Linguistics.