<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schmitt-etal-2024-tppmi">
    <titleInfo>
        <title>TPPMI - a Temporal Positive Pointwise Mutual Information Embedding of Words</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Paul</namePart>
        <namePart type="family">Schmitt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zsófia</namePart>
        <namePart type="family">Rakovics</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Márton</namePart>
        <namePart type="family">Rakovics</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gábor</namePart>
        <namePart type="family">Recski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 4th Workshop on Computational Linguistics for the Political and Social Sciences: Long and short papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Klamm</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gabriella</namePart>
            <namePart type="family">Lapesa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simone</namePart>
            <namePart type="given">Paolo</namePart>
            <namePart type="family">Ponzetto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ines</namePart>
            <namePart type="family">Rehbein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Indira</namePart>
            <namePart type="family">Sen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We present Temporal Positive Pointwise Mutual Information (TPPMI) embeddings as a robust and data-efficient alternative for modeling temporal semantic change. Based on the assumption that the semantics of the most frequent words in a corpus are relatively stable over time, our model represents words as vectors of their PPMI similarities with a predefined set of such context words. We evaluate our method on the temporal word analogy benchmark of Yao et al. (2018) and compare it to the TWEC model (Di Carlo et al., 2019), demonstrating the competitiveness of the approach. While the performance of TPPMI stays below that of the state-of-the-art TWEC model, it offers a higher degree of interpretability and is applicable in scenarios where only a limited amount of data is available.</abstract>
    <identifier type="citekey">schmitt-etal-2024-tppmi</identifier>
    <location>
        <url>https://aclanthology.org/2024.cpss-1.10</url>
    </location>
    <part>
        <date>2024-09</date>
        <extent unit="page">
            <start>119</start>
            <end>125</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T TPPMI - a Temporal Positive Pointwise Mutual Information Embedding of Words
%A Schmitt, Paul
%A Rakovics, Zsófia
%A Rakovics, Márton
%A Recski, Gábor
%Y Klamm, Christopher
%Y Lapesa, Gabriella
%Y Ponzetto, Simone Paolo
%Y Rehbein, Ines
%Y Sen, Indira
%S Proceedings of the 4th Workshop on Computational Linguistics for the Political and Social Sciences: Long and short papers
%D 2024
%8 September
%I Association for Computational Linguistics
%C Vienna, Austria
%F schmitt-etal-2024-tppmi
%X We present Temporal Positive Pointwise Mutual Information (TPPMI) embeddings as a robust and data-efficient alternative for modeling temporal semantic change. Based on the assumption that the semantics of the most frequent words in a corpus are relatively stable over time, our model represents words as vectors of their PPMI similarities with a predefined set of such context words. We evaluate our method on the temporal word analogy benchmark of Yao et al. (2018) and compare it to the TWEC model (Di Carlo et al., 2019), demonstrating the competitiveness of the approach. While the performance of TPPMI stays below that of the state-of-the-art TWEC model, it offers a higher degree of interpretability and is applicable in scenarios where only a limited amount of data is available.
%U https://aclanthology.org/2024.cpss-1.10
%P 119-125

Markdown (Informal)

[TPPMI - a Temporal Positive Pointwise Mutual Information Embedding of Words](https://aclanthology.org/2024.cpss-1.10) (Schmitt et al., cpss-WS 2024)

• TPPMI - a Temporal Positive Pointwise Mutual Information Embedding of Words (Schmitt et al., cpss-WS 2024)

ACL

• Paul Schmitt, Zsófia Rakovics, Márton Rakovics, and Gábor Recski. 2024. TPPMI - a Temporal Positive Pointwise Mutual Information Embedding of Words. In Proceedings of the 4th Workshop on Computational Linguistics for the Political and Social Sciences: Long and short papers, pages 119–125, Vienna, Austria. Association for Computational Linguistics.