<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naim-etal-2018-feature">
    <titleInfo>
        <title>Feature-Based Decipherment for Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Iftekhar</namePart>
        <namePart type="family">Naim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Parker</namePart>
        <namePart type="family">Riley</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Gildea</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>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 authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Orthographic similarities across languages provide a strong signal for unsupervised probabilistic transduction (decipherment) for closely related language pairs. The existing decipherment models, however, are not well suited for exploiting these orthographic similarities. We propose a log-linear model with latent variables that incorporates orthographic similarity features. Maximum likelihood training is computationally expensive for the proposed log-linear model. To address this challenge, we perform approximate inference via Markov chain Monte Carlo sampling and contrastive divergence. Our results show that the proposed log-linear model with contrastive divergence outperforms the existing generative decipherment models by exploiting the orthographic features. The model both scales to large vocabularies and preserves accuracy in low- and no-resource contexts.</abstract>
    <identifier type="citekey">naim-etal-2018-feature</identifier>
    <identifier type="doi">10.1162/coli_a_00326</identifier>
    <location>
        <url>https://aclanthology.org/J18-3006</url>
    </location>
    <part>
        <date>2018-09</date>
        <detail type="volume"><number>44</number></detail>
        <detail type="issue"><number>3</number></detail>
        <extent unit="page">
            <start>525</start>
            <end>546</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Feature-Based Decipherment for Machine Translation
%A Naim, Iftekhar
%A Riley, Parker
%A Gildea, Daniel
%J Computational Linguistics
%D 2018
%8 September
%V 44
%N 3
%I MIT Press
%C Cambridge, MA
%F naim-etal-2018-feature
%X Orthographic similarities across languages provide a strong signal for unsupervised probabilistic transduction (decipherment) for closely related language pairs. The existing decipherment models, however, are not well suited for exploiting these orthographic similarities. We propose a log-linear model with latent variables that incorporates orthographic similarity features. Maximum likelihood training is computationally expensive for the proposed log-linear model. To address this challenge, we perform approximate inference via Markov chain Monte Carlo sampling and contrastive divergence. Our results show that the proposed log-linear model with contrastive divergence outperforms the existing generative decipherment models by exploiting the orthographic features. The model both scales to large vocabularies and preserves accuracy in low- and no-resource contexts.
%R 10.1162/coli_a_00326
%U https://aclanthology.org/J18-3006
%U https://doi.org/10.1162/coli_a_00326
%P 525-546

Markdown (Informal)

[Feature-Based Decipherment for Machine Translation](https://aclanthology.org/J18-3006) (Naim et al., CL 2018)

• Feature-Based Decipherment for Machine Translation (Naim et al., CL 2018)

ACL

• Iftekhar Naim, Parker Riley, and Daniel Gildea. 2018. Feature-Based Decipherment for Machine Translation. Computational Linguistics, 44(3):525–546.