<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barak-goldberg-2019-evaluating">
    <titleInfo>
        <title>Evaluating Ways of Adapting Word Similarity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Libby</namePart>
        <namePart type="family">Barak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Adele</namePart>
        <namePart type="family">Goldberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2019 Workshop on Widening NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Amittai</namePart>
            <namePart type="family">Axelrod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Diyi</namePart>
            <namePart type="family">Yang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rossana</namePart>
            <namePart type="family">Cunha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Samira</namePart>
            <namePart type="family">Shaikh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zeerak</namePart>
            <namePart type="family">Waseem</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>People judge pairwise similarity by deciding which aspects of the words’ meanings are relevant for the comparison of the given pair. However, computational representations of meaning rely on dimensions of the vector representation for similarity comparisons, without considering the specific pairing at hand. Prior work has adapted computational similarity judgments by using the softmax function in order to address this limitation by capturing asymmetry in human judgments. We extend this analysis by showing that a simple modification of cosine similarity offers a better correlation with human judgments over a comprehensive dataset. The modification performs best when the similarity between two words is calculated with reference to other words that are most similar and dissimilar to the pair.</abstract>
    <identifier type="citekey">barak-goldberg-2019-evaluating</identifier>
    <location>
        <url>https://aclanthology.org/W19-3639</url>
    </location>
    <part>
        <date>2019-08</date>
        <extent unit="page">
            <start>126</start>
            <end>128</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Evaluating Ways of Adapting Word Similarity
%A Barak, Libby
%A Goldberg, Adele
%Y Axelrod, Amittai
%Y Yang, Diyi
%Y Cunha, Rossana
%Y Shaikh, Samira
%Y Waseem, Zeerak
%S Proceedings of the 2019 Workshop on Widening NLP
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F barak-goldberg-2019-evaluating
%X People judge pairwise similarity by deciding which aspects of the words’ meanings are relevant for the comparison of the given pair. However, computational representations of meaning rely on dimensions of the vector representation for similarity comparisons, without considering the specific pairing at hand. Prior work has adapted computational similarity judgments by using the softmax function in order to address this limitation by capturing asymmetry in human judgments. We extend this analysis by showing that a simple modification of cosine similarity offers a better correlation with human judgments over a comprehensive dataset. The modification performs best when the similarity between two words is calculated with reference to other words that are most similar and dissimilar to the pair.
%U https://aclanthology.org/W19-3639
%P 126-128

Markdown (Informal)

[Evaluating Ways of Adapting Word Similarity](https://aclanthology.org/W19-3639) (Barak & Goldberg, WiNLP 2019)

• Evaluating Ways of Adapting Word Similarity (Barak & Goldberg, WiNLP 2019)

ACL

• Libby Barak and Adele Goldberg. 2019. Evaluating Ways of Adapting Word Similarity. In Proceedings of the 2019 Workshop on Widening NLP, pages 126–128, Florence, Italy. Association for Computational Linguistics.