<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bisazza-federico-2013-dynamically">
    <titleInfo>
        <title>Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation</title>
    </titleInfo>
    <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">Marcello</namePart>
        <namePart type="family">Federico</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2013</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre>journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre>academic journal</genre>
    </relatedItem>
    <abstract>Defining the reordering search space is a crucial issue in phrase-based SMT between distant languages. In fact, the optimal trade-off between accuracy and complexity of decoding is nowadays reached by harshly limiting the input permutation space. We propose a method to dynamically shape such space and, thus, capture long-range word movements without hurting translation quality nor decoding time. The space defined by loose reordering constraints is dynamically pruned through a binary classifier that predicts whether a given input word should be translated right after another. The integration of this model into a phrase-based decoder improves a strong Arabic-English baseline already including state-of-the-art early distortion cost (Moore and Quirk, 2007) and hierarchical phrase orientation models (Galley and Manning, 2008). Significant improvements in the reordering of verbs are achieved by a system that is notably faster than the baseline, while bleu and meteor remain stable, or even increase, at a very high distortion limit.</abstract>
    <identifier type="citekey">bisazza-federico-2013-dynamically</identifier>
    <identifier type="doi">10.1162/tacl_a_00231</identifier>
    <location>
        <url>https://aclanthology.org/Q13-1027</url>
    </location>
    <part>
        <date>2013</date>
        <detail type="volume"><number>1</number></detail>
        <extent unit="page">
            <start>327</start>
            <end>340</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation
%A Bisazza, Arianna
%A Federico, Marcello
%J Transactions of the Association for Computational Linguistics
%D 2013
%V 1
%I MIT Press
%C Cambridge, MA
%F bisazza-federico-2013-dynamically
%X Defining the reordering search space is a crucial issue in phrase-based SMT between distant languages. In fact, the optimal trade-off between accuracy and complexity of decoding is nowadays reached by harshly limiting the input permutation space. We propose a method to dynamically shape such space and, thus, capture long-range word movements without hurting translation quality nor decoding time. The space defined by loose reordering constraints is dynamically pruned through a binary classifier that predicts whether a given input word should be translated right after another. The integration of this model into a phrase-based decoder improves a strong Arabic-English baseline already including state-of-the-art early distortion cost (Moore and Quirk, 2007) and hierarchical phrase orientation models (Galley and Manning, 2008). Significant improvements in the reordering of verbs are achieved by a system that is notably faster than the baseline, while bleu and meteor remain stable, or even increase, at a very high distortion limit.
%9 journal article
%R 10.1162/tacl_a_00231
%U https://aclanthology.org/Q13-1027
%U https://doi.org/10.1162/tacl_a_00231
%P 327-340

Markdown (Informal)

[Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation](https://aclanthology.org/Q13-1027) (Bisazza & Federico, TACL 2013)

• Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation (Bisazza & Federico, TACL 2013)

ACL

• Arianna Bisazza and Marcello Federico. 2013. Dynamically Shaping the Reordering Search Space of Phrase-Based Statistical Machine Translation. Transactions of the Association for Computational Linguistics, 1:327–340.