<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahrainian-etal-2021-self-supervised">
    <titleInfo>
        <title>Self-Supervised Neural Topic Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seyed</namePart>
        <namePart type="given">Ali</namePart>
        <namePart type="family">Bahrainian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martin</namePart>
        <namePart type="family">Jaggi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carsten</namePart>
        <namePart type="family">Eickhoff</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Topic models are useful tools for analyzing and interpreting the main underlying themes of large corpora of text. Most topic models rely on word co-occurrence for computing a topic, i.e., a weighted set of words that together represent a high-level semantic concept. In this paper, we propose a new light-weight Self-Supervised Neural Topic Model (SNTM) that learns a rich context by learning a topic representation jointly from three co-occurring words and a document that the triple originates from. Our experimental results indicate that our proposed neural topic model, SNTM, outperforms previously existing topic models in coherence metrics as well as document clustering accuracy. Moreover, apart from the topic coherence and clustering performance, the proposed neural topic model has a number of advantages, namely, being computationally efficient and easy to train.</abstract>
    <identifier type="citekey">bahrainian-etal-2021-self-supervised</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.284</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.284</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>3341</start>
            <end>3350</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-Supervised Neural Topic Modeling
%A Bahrainian, Seyed Ali
%A Jaggi, Martin
%A Eickhoff, Carsten
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F bahrainian-etal-2021-self-supervised
%X Topic models are useful tools for analyzing and interpreting the main underlying themes of large corpora of text. Most topic models rely on word co-occurrence for computing a topic, i.e., a weighted set of words that together represent a high-level semantic concept. In this paper, we propose a new light-weight Self-Supervised Neural Topic Model (SNTM) that learns a rich context by learning a topic representation jointly from three co-occurring words and a document that the triple originates from. Our experimental results indicate that our proposed neural topic model, SNTM, outperforms previously existing topic models in coherence metrics as well as document clustering accuracy. Moreover, apart from the topic coherence and clustering performance, the proposed neural topic model has a number of advantages, namely, being computationally efficient and easy to train.
%R 10.18653/v1/2021.findings-emnlp.284
%U https://aclanthology.org/2021.findings-emnlp.284
%U https://doi.org/10.18653/v1/2021.findings-emnlp.284
%P 3341-3350

Markdown (Informal)

[Self-Supervised Neural Topic Modeling](https://aclanthology.org/2021.findings-emnlp.284) (Bahrainian et al., Findings 2021)

• Self-Supervised Neural Topic Modeling (Bahrainian et al., Findings 2021)

ACL

• Seyed Ali Bahrainian, Martin Jaggi, and Carsten Eickhoff. 2021. Self-Supervised Neural Topic Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3341–3350, Punta Cana, Dominican Republic. Association for Computational Linguistics.