<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakov-vogel-2017-robust">
    <titleInfo>
        <title>Robust Tuning Datasets for Statistical Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Preslav</namePart>
        <namePart type="family">Nakov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stephan</namePart>
        <namePart type="family">Vogel</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 International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning algorithms. This is an under-explored research direction, which can allow better parameter tuning. In this paper, we achieve this goal by selecting a subset of the available sentence pairs, which are more suitable for specific combinations of optimizers, objective functions, and evaluation measures. We demonstrate the potential of the idea with the pairwise ranking optimization (PRO) optimizer, which is known to yield too short translations. We show that the learning problem can be alleviated by tuning on a subset of the development set, selected based on sentence length. In particular, using the longest 50% of the tuning sentences, we achieve two-fold tuning speedup, and improvements in BLEU score that rival those of alternatives, which fix BLEU+1’s smoothing instead.</abstract>
    <identifier type="citekey">nakov-vogel-2017-robust</identifier>
    <identifier type="doi">10.26615/978-954-452-049-6_071</identifier>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>543</start>
            <end>550</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Robust Tuning Datasets for Statistical Machine Translation
%A Nakov, Preslav
%A Vogel, Stephan
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F nakov-vogel-2017-robust
%X We explore the idea of automatically crafting a tuning dataset for Statistical Machine Translation (SMT) that makes the hyper-parameters of the SMT system more robust with respect to some specific deficiencies of the parameter tuning algorithms. This is an under-explored research direction, which can allow better parameter tuning. In this paper, we achieve this goal by selecting a subset of the available sentence pairs, which are more suitable for specific combinations of optimizers, objective functions, and evaluation measures. We demonstrate the potential of the idea with the pairwise ranking optimization (PRO) optimizer, which is known to yield too short translations. We show that the learning problem can be alleviated by tuning on a subset of the development set, selected based on sentence length. In particular, using the longest 50% of the tuning sentences, we achieve two-fold tuning speedup, and improvements in BLEU score that rival those of alternatives, which fix BLEU+1’s smoothing instead.
%R 10.26615/978-954-452-049-6_071
%U https://doi.org/10.26615/978-954-452-049-6_071
%P 543-550

Markdown (Informal)

[Robust Tuning Datasets for Statistical Machine Translation](https://doi.org/10.26615/978-954-452-049-6_071) (Nakov & Vogel, RANLP 2017)

• Robust Tuning Datasets for Statistical Machine Translation (Nakov & Vogel, RANLP 2017)

ACL

• Preslav Nakov and Stephan Vogel. 2017. Robust Tuning Datasets for Statistical Machine Translation. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 543–550, Varna, Bulgaria. INCOMA Ltd..