<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wojciechowski-etal-2024-faithful">
    <titleInfo>
        <title>Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Adam</namePart>
        <namePart type="family">Wojciechowski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mateusz</namePart>
        <namePart type="family">Lango</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Dusek</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural language explanation method that can be applied to any CNN-based classifier without altering its training process or affecting predictive performance. By analysing influential neurons and the corresponding activation maps, the method generates a faithful description of the classifier’s decision process in the form of a structured meaning representation, which is then converted into text by a language model. Through this pipeline approach, the generated explanations are grounded in the neural network architecture, providing accurate insight into the classification process while remaining accessible to non-experts. Experimental results show that the NLEs constructed by our method are significantly more plausible and faithful than baselines. In particular, user interventions in the neural network structure (masking of neurons) are three times more effective.</abstract>
    <identifier type="citekey">wojciechowski-etal-2024-faithful</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.130</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>2340</start>
            <end>2351</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach
%A Wojciechowski, Adam
%A Lango, Mateusz
%A Dusek, Ondrej
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F wojciechowski-etal-2024-faithful
%X Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural language explanation method that can be applied to any CNN-based classifier without altering its training process or affecting predictive performance. By analysing influential neurons and the corresponding activation maps, the method generates a faithful description of the classifier’s decision process in the form of a structured meaning representation, which is then converted into text by a language model. Through this pipeline approach, the generated explanations are grounded in the neural network architecture, providing accurate insight into the classification process while remaining accessible to non-experts. Experimental results show that the NLEs constructed by our method are significantly more plausible and faithful than baselines. In particular, user interventions in the neural network structure (masking of neurons) are three times more effective.
%U https://aclanthology.org/2024.findings-emnlp.130
%P 2340-2351

Markdown (Informal)

[Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach](https://aclanthology.org/2024.findings-emnlp.130) (Wojciechowski et al., Findings 2024)

• Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach (Wojciechowski et al., Findings 2024)

ACL

• Adam Wojciechowski, Mateusz Lango, and Ondrej Dusek. 2024. Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2340–2351, Miami, Florida, USA. Association for Computational Linguistics.