<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-novel">
    <titleInfo>
        <title>A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dairui</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Derek</namePart>
        <namePart type="family">Greene</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruihai</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Many recent deep learning-based solutions have adopted the attention mechanism in various tasks in the field of NLP. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism increase the models’ complexity, thus leading to challenges in model explainability. To address this challenge, we propose a novel practical framework by utilizing a two-tier attention architecture to decouple the complexity of explanation and the decision-making process. We apply it in the context of a news article classification task. The experiments on two large-scaled news corpora demonstrate that the proposed model can achieve competitive performance with many state-of-the-art alternatives and illustrate its appropriateness from an explainability perspective. We release the source code here.</abstract>
    <identifier type="citekey">liu-etal-2022-novel</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.178</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.178</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>2280</start>
            <end>2290</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification
%A Liu, Dairui
%A Greene, Derek
%A Dong, Ruihai
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F liu-etal-2022-novel
%X Many recent deep learning-based solutions have adopted the attention mechanism in various tasks in the field of NLP. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism increase the models’ complexity, thus leading to challenges in model explainability. To address this challenge, we propose a novel practical framework by utilizing a two-tier attention architecture to decouple the complexity of explanation and the decision-making process. We apply it in the context of a news article classification task. The experiments on two large-scaled news corpora demonstrate that the proposed model can achieve competitive performance with many state-of-the-art alternatives and illustrate its appropriateness from an explainability perspective. We release the source code here.
%R 10.18653/v1/2022.findings-acl.178
%U https://aclanthology.org/2022.findings-acl.178
%U https://doi.org/10.18653/v1/2022.findings-acl.178
%P 2280-2290

Markdown (Informal)

[A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification](https://aclanthology.org/2022.findings-acl.178) (Liu et al., Findings 2022)

• A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification (Liu et al., Findings 2022)

ACL

• Dairui Liu, Derek Greene, and Ruihai Dong. 2022. A Novel Perspective to Look At Attention: Bi-level Attention-based Explainable Topic Modeling for News Classification. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2280–2290, Dublin, Ireland. Association for Computational Linguistics.