<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martindale-2012-statistical">
    <titleInfo>
        <title>Can Statistical Post-Editing with a Small Parallel Corpus Save a Weak MT Engine?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marianna</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Martindale</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2012-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC‘12)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nicoletta</namePart>
            <namePart type="family">Calzolari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Khalid</namePart>
            <namePart type="family">Choukri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thierry</namePart>
            <namePart type="family">Declerck</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mehmet</namePart>
            <namePart type="given">Uğur</namePart>
            <namePart type="family">Doğan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bente</namePart>
            <namePart type="family">Maegaard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joseph</namePart>
            <namePart type="family">Mariani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Asuncion</namePart>
            <namePart type="family">Moreno</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jan</namePart>
            <namePart type="family">Odijk</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>European Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Istanbul, Turkey</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Statistical post-editing has been shown in several studies to increase BLEU score for rule-based MT systems. However, previous studies have relied solely on BLEU and have not conducted further study to determine whether those gains indicated an increase in quality or in score alone. In this work we conduct a human evaluation of statistical post-edited output from a weak rule-based MT system, comparing the results with the output of the original rule-based system and a phrase-based statistical MT system trained on the same data. We show that for this weak rule-based system, despite significant BLEU score increases, human evaluators prefer the output of the original system. While this is not a generally conclusive condemnation of statistical post-editing, this result does cast doubt on the efficacy of statistical post-editing for weak MT systems and on the reliability of BLEU score for comparison between weak rule-based and hybrid systems built from them.</abstract>
    <identifier type="citekey">martindale-2012-statistical</identifier>
    <location>
        <url>https://aclanthology.org/L12-1055/</url>
    </location>
    <part>
        <date>2012-05</date>
        <extent unit="page">
            <start>2138</start>
            <end>2142</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Can Statistical Post-Editing with a Small Parallel Corpus Save a Weak MT Engine?
%A Martindale, Marianna J.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC‘12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F martindale-2012-statistical
%X Statistical post-editing has been shown in several studies to increase BLEU score for rule-based MT systems. However, previous studies have relied solely on BLEU and have not conducted further study to determine whether those gains indicated an increase in quality or in score alone. In this work we conduct a human evaluation of statistical post-edited output from a weak rule-based MT system, comparing the results with the output of the original rule-based system and a phrase-based statistical MT system trained on the same data. We show that for this weak rule-based system, despite significant BLEU score increases, human evaluators prefer the output of the original system. While this is not a generally conclusive condemnation of statistical post-editing, this result does cast doubt on the efficacy of statistical post-editing for weak MT systems and on the reliability of BLEU score for comparison between weak rule-based and hybrid systems built from them.
%U https://aclanthology.org/L12-1055/
%P 2138-2142

Markdown (Informal)

[Can Statistical Post-Editing with a Small Parallel Corpus Save a Weak MT Engine?](https://aclanthology.org/L12-1055/) (Martindale, LREC 2012)

• Can Statistical Post-Editing with a Small Parallel Corpus Save a Weak MT Engine? (Martindale, LREC 2012)

ACL

• Marianna J. Martindale. 2012. Can Statistical Post-Editing with a Small Parallel Corpus Save a Weak MT Engine?. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2138–2142, Istanbul, Turkey. European Language Resources Association (ELRA).