<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2023-asymmetric">
    <titleInfo>
        <title>Asymmetric feature interaction for interpreting model predictions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaolei</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianghong</namePart>
        <namePart type="family">Ma</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Haode</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In natural language processing (NLP), deep neural networks (DNNs) could model complex interactions between context and have achieved impressive results on a range of NLP tasks. Prior works on feature interaction attribution mainly focus on studying symmetric interaction that only explains the additional influence of a set of words in combination, which fails to capture asymmetric influence that contributes to model prediction. In this work, we propose an asymmetric feature interaction attribution explanation model that aims to explore asymmetric higher-order feature interactions in the inference of deep neural NLP models. By representing our explanation with an directed interaction graph, we experimentally demonstrate interpretability of the graph to discover asymmetric feature interactions. Experimental results on two sentiment classification datasets show the superiority of our model against the state-of-the-art feature interaction attribution methods in identifying influential features for model predictions.</abstract>
    <identifier type="citekey">lu-etal-2023-asymmetric</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.286</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.286</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>4666</start>
            <end>4678</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Asymmetric feature interaction for interpreting model predictions
%A Lu, Xiaolei
%A Ma, Jianghong
%A Zhang, Haode
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lu-etal-2023-asymmetric
%X In natural language processing (NLP), deep neural networks (DNNs) could model complex interactions between context and have achieved impressive results on a range of NLP tasks. Prior works on feature interaction attribution mainly focus on studying symmetric interaction that only explains the additional influence of a set of words in combination, which fails to capture asymmetric influence that contributes to model prediction. In this work, we propose an asymmetric feature interaction attribution explanation model that aims to explore asymmetric higher-order feature interactions in the inference of deep neural NLP models. By representing our explanation with an directed interaction graph, we experimentally demonstrate interpretability of the graph to discover asymmetric feature interactions. Experimental results on two sentiment classification datasets show the superiority of our model against the state-of-the-art feature interaction attribution methods in identifying influential features for model predictions.
%R 10.18653/v1/2023.findings-acl.286
%U https://aclanthology.org/2023.findings-acl.286
%U https://doi.org/10.18653/v1/2023.findings-acl.286
%P 4666-4678

Markdown (Informal)

[Asymmetric feature interaction for interpreting model predictions](https://aclanthology.org/2023.findings-acl.286) (Lu et al., Findings 2023)

• Asymmetric feature interaction for interpreting model predictions (Lu et al., Findings 2023)

ACL

• Xiaolei Lu, Jianghong Ma, and Haode Zhang. 2023. Asymmetric feature interaction for interpreting model predictions. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4666–4678, Toronto, Canada. Association for Computational Linguistics.