<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fiacco-etal-2019-deep">
    <titleInfo>
        <title>Deep Neural Model Inspection and Comparison via Functional Neuron Pathways</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">James</namePart>
        <namePart type="family">Fiacco</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Samridhi</namePart>
        <namePart type="family">Choudhary</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Carolyn</namePart>
        <namePart type="family">Rose</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We introduce a general method for the interpretation and comparison of neural models. The method is used to factor a complex neural model into its functional components, which are comprised of sets of co-firing neurons that cut across layers of the network architecture, and which we call neural pathways. The function of these pathways can be understood by identifying correlated task level and linguistic heuristics in such a way that this knowledge acts as a lens for approximating what the network has learned to apply to its intended task. As a case study for investigating the utility of these pathways, we present an examination of pathways identified in models trained for two standard tasks, namely Named Entity Recognition and Recognizing Textual Entailment.</abstract>
    <identifier type="citekey">fiacco-etal-2019-deep</identifier>
    <identifier type="doi">10.18653/v1/P19-1575</identifier>
    <location>
        <url>https://aclanthology.org/P19-1575</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>5754</start>
            <end>5764</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Deep Neural Model Inspection and Comparison via Functional Neuron Pathways
%A Fiacco, James
%A Choudhary, Samridhi
%A Rose, Carolyn
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F fiacco-etal-2019-deep
%X We introduce a general method for the interpretation and comparison of neural models. The method is used to factor a complex neural model into its functional components, which are comprised of sets of co-firing neurons that cut across layers of the network architecture, and which we call neural pathways. The function of these pathways can be understood by identifying correlated task level and linguistic heuristics in such a way that this knowledge acts as a lens for approximating what the network has learned to apply to its intended task. As a case study for investigating the utility of these pathways, we present an examination of pathways identified in models trained for two standard tasks, namely Named Entity Recognition and Recognizing Textual Entailment.
%R 10.18653/v1/P19-1575
%U https://aclanthology.org/P19-1575
%U https://doi.org/10.18653/v1/P19-1575
%P 5754-5764

Markdown (Informal)

[Deep Neural Model Inspection and Comparison via Functional Neuron Pathways](https://aclanthology.org/P19-1575) (Fiacco et al., ACL 2019)

• Deep Neural Model Inspection and Comparison via Functional Neuron Pathways (Fiacco et al., ACL 2019)

ACL

• James Fiacco, Samridhi Choudhary, and Carolyn Rose. 2019. Deep Neural Model Inspection and Comparison via Functional Neuron Pathways. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5754–5764, Florence, Italy. Association for Computational Linguistics.