<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zosa-etal-2020-comparison">
    <titleInfo>
        <title>A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Elaine</namePart>
        <namePart type="family">Zosa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mark</namePart>
        <namePart type="family">Granroth-Wilding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lidia</namePart>
        <namePart type="family">Pivovarova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">English</languageTerm>
        <languageTerm type="code" authority="iso639-2b">eng</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kathy</namePart>
            <namePart type="family">McKeown</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Douglas</namePart>
            <namePart type="given">W</namePart>
            <namePart type="family">Oard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name>
            <namePart>Elizabeth</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Richard</namePart>
            <namePart type="family">Schwartz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>European Language Resources Association</publisher>
            <place>
                <placeTerm type="text">Marseille, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-10-95546-55-9</identifier>
    </relatedItem>
    <abstract>We address the problem of linking related documents across languages in a multilingual collection. We evaluate three diverse unsupervised methods to represent and compare documents: (1) multilingual topic model; (2) cross-lingual document embeddings; and (3) Wasserstein distance. We test the performance of these methods in retrieving news articles in Swedish that are known to be related to a given Finnish article. The results show that ensembles of the methods outperform the stand-alone methods, suggesting that they capture complementary characteristics of the documents</abstract>
    <identifier type="citekey">zosa-etal-2020-comparison</identifier>
    <location>
        <url>https://aclanthology.org/2020.clssts-1.6</url>
    </location>
    <part>
        <date>2020-05</date>
        <extent unit="page">
            <start>32</start>
            <end>37</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval
%A Zosa, Elaine
%A Granroth-Wilding, Mark
%A Pivovarova, Lidia
%Y McKeown, Kathy
%Y Oard, Douglas W.
%Y Schwartz, Richard
%E Elizabeth
%S Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020)
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-55-9
%G English
%F zosa-etal-2020-comparison
%X We address the problem of linking related documents across languages in a multilingual collection. We evaluate three diverse unsupervised methods to represent and compare documents: (1) multilingual topic model; (2) cross-lingual document embeddings; and (3) Wasserstein distance. We test the performance of these methods in retrieving news articles in Swedish that are known to be related to a given Finnish article. The results show that ensembles of the methods outperform the stand-alone methods, suggesting that they capture complementary characteristics of the documents
%U https://aclanthology.org/2020.clssts-1.6
%P 32-37

Markdown (Informal)

[A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval](https://aclanthology.org/2020.clssts-1.6) (Zosa et al., CLSSTS 2020)

• A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval (Zosa et al., CLSSTS 2020)

ACL

• Elaine Zosa, Mark Granroth-Wilding, and Lidia Pivovarova. 2020. A Comparison of Unsupervised Methods for Ad hoc Cross-Lingual Document Retrieval. In Proceedings of the workshop on Cross-Language Search and Summarization of Text and Speech (CLSSTS2020), pages 32–37, Marseille, France. European Language Resources Association.