<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="briakou-etal-2019-cross">
    <titleInfo>
        <title>Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Eleftheria</namePart>
        <namePart type="family">Briakou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nikos</namePart>
        <namePart type="family">Athanasiou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandros</namePart>
        <namePart type="family">Potamianos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jill</namePart>
            <namePart type="family">Burstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christy</namePart>
            <namePart type="family">Doran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thamar</namePart>
            <namePart type="family">Solorio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Minneapolis, Minnesota</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a word based on different topics. First, a separate DSM is trained for each topic and then each of the topic-based DSMs is aligned to a common vector space. Our unsupervised mapping approach is motivated by the hypothesis that words preserving their relative distances in different topic semantic sub-spaces constitute robust semantic anchors that define the mappings between them. Aligned cross-topic representations achieve state-of-the-art results for the task of contextual word similarity. Furthermore, evaluation on NLP downstream tasks shows that multiple topic-based embeddings outperform single-prototype models.</abstract>
    <identifier type="citekey">briakou-etal-2019-cross</identifier>
    <identifier type="doi">10.18653/v1/N19-1110</identifier>
    <location>
        <url>https://aclanthology.org/N19-1110</url>
    </location>
    <part>
        <date>2019-06</date>
        <extent unit="page">
            <start>1052</start>
            <end>1061</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings
%A Briakou, Eleftheria
%A Athanasiou, Nikos
%A Potamianos, Alexandros
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F briakou-etal-2019-cross
%X In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a word based on different topics. First, a separate DSM is trained for each topic and then each of the topic-based DSMs is aligned to a common vector space. Our unsupervised mapping approach is motivated by the hypothesis that words preserving their relative distances in different topic semantic sub-spaces constitute robust semantic anchors that define the mappings between them. Aligned cross-topic representations achieve state-of-the-art results for the task of contextual word similarity. Furthermore, evaluation on NLP downstream tasks shows that multiple topic-based embeddings outperform single-prototype models.
%R 10.18653/v1/N19-1110
%U https://aclanthology.org/N19-1110
%U https://doi.org/10.18653/v1/N19-1110
%P 1052-1061

Markdown (Informal)

[Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings](https://aclanthology.org/N19-1110) (Briakou et al., NAACL 2019)

• Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings (Briakou et al., NAACL 2019)

ACL

• Eleftheria Briakou, Nikos Athanasiou, and Alexandros Potamianos. 2019. Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1052–1061, Minneapolis, Minnesota. Association for Computational Linguistics.