<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-lauw-2022-towards">
    <titleInfo>
        <title>Towards Reinterpreting Neural Topic Models via Composite Activations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jia</namePart>
        <namePart type="given">Peng</namePart>
        <namePart type="family">Lim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hady</namePart>
        <namePart type="family">Lauw</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Most Neural Topic Models (NTM) use a variational auto-encoder framework producing K topics limited to the size of the encoder’s output. These topics are interpreted through the selection of the top activated words via the weights or reconstructed vector of the decoder that are directly connected to each neuron. In this paper, we present a model-free two-stage process to reinterpret NTM and derive further insights on the state of the trained model. Firstly, building on the original information from a trained NTM, we generate a pool of potential candidate “composite topics” by exploiting possible co-occurrences within the original set of topics, which decouples the strict interpretation of topics from the original NTM. This is followed by a combinatorial formulation to select a final set of composite topics, which we evaluate for coherence and diversity on a large external corpus. Lastly, we employ a user study to derive further insights on the reinterpretation process.</abstract>
    <identifier type="citekey">lim-lauw-2022-towards</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.242</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.242</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>3688</start>
            <end>3703</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Reinterpreting Neural Topic Models via Composite Activations
%A Lim, Jia Peng
%A Lauw, Hady
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F lim-lauw-2022-towards
%X Most Neural Topic Models (NTM) use a variational auto-encoder framework producing K topics limited to the size of the encoder’s output. These topics are interpreted through the selection of the top activated words via the weights or reconstructed vector of the decoder that are directly connected to each neuron. In this paper, we present a model-free two-stage process to reinterpret NTM and derive further insights on the state of the trained model. Firstly, building on the original information from a trained NTM, we generate a pool of potential candidate “composite topics” by exploiting possible co-occurrences within the original set of topics, which decouples the strict interpretation of topics from the original NTM. This is followed by a combinatorial formulation to select a final set of composite topics, which we evaluate for coherence and diversity on a large external corpus. Lastly, we employ a user study to derive further insights on the reinterpretation process.
%R 10.18653/v1/2022.emnlp-main.242
%U https://aclanthology.org/2022.emnlp-main.242
%U https://doi.org/10.18653/v1/2022.emnlp-main.242
%P 3688-3703

Markdown (Informal)

[Towards Reinterpreting Neural Topic Models via Composite Activations](https://aclanthology.org/2022.emnlp-main.242) (Lim & Lauw, EMNLP 2022)

• Towards Reinterpreting Neural Topic Models via Composite Activations (Lim & Lauw, EMNLP 2022)

ACL

• Jia Peng Lim and Hady Lauw. 2022. Towards Reinterpreting Neural Topic Models via Composite Activations. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3688–3703, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.