<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marchisio-etal-2022-embedding">
    <titleInfo>
        <title>Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kelly</namePart>
        <namePart type="family">Marchisio</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Conghao</namePart>
        <namePart type="family">Xiong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Koehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Francisco</namePart>
            <namePart type="family">Guzmán</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">Orlando, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. New methods that outperform GIZA++ primarily rely on large machine translation models, massively multilingual language models, or supervision from GIZA++ alignments itself. We introduce Embedding-Enhanced GIZA++, and outperform GIZA++ without any of the aforementioned factors. Taking advantage of monolingual embedding spaces of source and target language only, we exceed GIZA++’s performance in every tested scenario for three languages pairs. In the lowest-resource setting, we outperform GIZA++ by 8.5, 10.9, and 12 AER for RoEn, De-En, and En-Fr, respectively. We release our code at www.blind-review.code.</abstract>
    <identifier type="citekey">marchisio-etal-2022-embedding</identifier>
    <location>
        <url>https://aclanthology.org/2022.amta-research.20</url>
    </location>
    <part>
        <date>2022-09</date>
        <extent unit="page">
            <start>264</start>
            <end>273</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings
%A Marchisio, Kelly
%A Xiong, Conghao
%A Koehn, Philipp
%Y Duh, Kevin
%Y Guzmán, Francisco
%S Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F marchisio-etal-2022-embedding
%X A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. New methods that outperform GIZA++ primarily rely on large machine translation models, massively multilingual language models, or supervision from GIZA++ alignments itself. We introduce Embedding-Enhanced GIZA++, and outperform GIZA++ without any of the aforementioned factors. Taking advantage of monolingual embedding spaces of source and target language only, we exceed GIZA++’s performance in every tested scenario for three languages pairs. In the lowest-resource setting, we outperform GIZA++ by 8.5, 10.9, and 12 AER for RoEn, De-En, and En-Fr, respectively. We release our code at www.blind-review.code.
%U https://aclanthology.org/2022.amta-research.20
%P 264-273

Markdown (Informal)

[Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings](https://aclanthology.org/2022.amta-research.20) (Marchisio et al., AMTA 2022)

• Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings (Marchisio et al., AMTA 2022)

ACL

• Kelly Marchisio, Conghao Xiong, and Philipp Koehn. 2022. Embedding-Enhanced GIZA++: Improving Low-Resource Word Alignment Using Embeddings. In Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 264–273, Orlando, USA. Association for Machine Translation in the Americas.