<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="szymanski-2017-temporal">
    <titleInfo>
        <title>Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Terrence</namePart>
        <namePart type="family">Szymanski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper introduces the concept of temporal word analogies: pairs of words which occupy the same semantic space at different points in time. One well-known property of word embeddings is that they are able to effectively model traditional word analogies (“word w₁ is to word w₂ as word w₃ is to word w₄”) through vector addition. Here, I show that temporal word analogies (“word w₁ at time t_α is like word w₂ at time t_β”) can effectively be modeled with diachronic word embeddings, provided that the independent embedding spaces from each time period are appropriately transformed into a common vector space. When applied to a diachronic corpus of news articles, this method is able to identify temporal word analogies such as “Ronald Reagan in 1987 is like Bill Clinton in 1997”, or “Walkman in 1987 is like iPod in 2007”.</abstract>
    <identifier type="citekey">szymanski-2017-temporal</identifier>
    <identifier type="doi">10.18653/v1/P17-2071</identifier>
    <location>
        <url>https://aclanthology.org/P17-2071</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>448</start>
            <end>453</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings
%A Szymanski, Terrence
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F szymanski-2017-temporal
%X This paper introduces the concept of temporal word analogies: pairs of words which occupy the same semantic space at different points in time. One well-known property of word embeddings is that they are able to effectively model traditional word analogies (“word w₁ is to word w₂ as word w₃ is to word w₄”) through vector addition. Here, I show that temporal word analogies (“word w₁ at time t_α is like word w₂ at time t_β”) can effectively be modeled with diachronic word embeddings, provided that the independent embedding spaces from each time period are appropriately transformed into a common vector space. When applied to a diachronic corpus of news articles, this method is able to identify temporal word analogies such as “Ronald Reagan in 1987 is like Bill Clinton in 1997”, or “Walkman in 1987 is like iPod in 2007”.
%R 10.18653/v1/P17-2071
%U https://aclanthology.org/P17-2071
%U https://doi.org/10.18653/v1/P17-2071
%P 448-453

Markdown (Informal)

[Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings](https://aclanthology.org/P17-2071) (Szymanski, ACL 2017)

• Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings (Szymanski, ACL 2017)

ACL

• Terrence Szymanski. 2017. Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 448–453, Vancouver, Canada. Association for Computational Linguistics.