<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahia-etal-2023-lexplain">
    <titleInfo>
        <title>LEXPLAIN: Improving Model Explanations via Lexicon Supervision</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Orevaoghene</namePart>
        <namePart type="family">Ahia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hila</namePart>
        <namePart type="family">Gonen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vidhisha</namePart>
        <namePart type="family">Balachandran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulia</namePart>
        <namePart type="family">Tsvetkov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noah</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Smith</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>Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Alexis</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jose</namePart>
            <namePart type="family">Camacho-collados</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>Model explanations that shed light on the model’s predictions are becoming a desired additional output of NLP models, alongside their predictions. Challenges in creating these explanations include making them trustworthy and faithful to the model’s predictions. In this work, we propose a novel framework for guiding model explanations by supervising them explicitly. To this end, our method, LEXplain, uses task-related lexicons to directly supervise model explanations. This approach consistently improves the model’s explanations without sacrificing performance on the task, as we demonstrate on sentiment analysis and toxicity detection. Our analyses show that our method also demotes spurious correlations (i.e., with respect to African American English dialect) when performing the task, improving fairness.</abstract>
    <identifier type="citekey">ahia-etal-2023-lexplain</identifier>
    <identifier type="doi">10.18653/v1/2023.starsem-1.19</identifier>
    <location>
        <url>https://aclanthology.org/2023.starsem-1.19</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>207</start>
            <end>216</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LEXPLAIN: Improving Model Explanations via Lexicon Supervision
%A Ahia, Orevaoghene
%A Gonen, Hila
%A Balachandran, Vidhisha
%A Tsvetkov, Yulia
%A Smith, Noah A.
%Y Palmer, Alexis
%Y Camacho-collados, Jose
%S Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ahia-etal-2023-lexplain
%X Model explanations that shed light on the model’s predictions are becoming a desired additional output of NLP models, alongside their predictions. Challenges in creating these explanations include making them trustworthy and faithful to the model’s predictions. In this work, we propose a novel framework for guiding model explanations by supervising them explicitly. To this end, our method, LEXplain, uses task-related lexicons to directly supervise model explanations. This approach consistently improves the model’s explanations without sacrificing performance on the task, as we demonstrate on sentiment analysis and toxicity detection. Our analyses show that our method also demotes spurious correlations (i.e., with respect to African American English dialect) when performing the task, improving fairness.
%R 10.18653/v1/2023.starsem-1.19
%U https://aclanthology.org/2023.starsem-1.19
%U https://doi.org/10.18653/v1/2023.starsem-1.19
%P 207-216

Markdown (Informal)

[LEXPLAIN: Improving Model Explanations via Lexicon Supervision](https://aclanthology.org/2023.starsem-1.19) (Ahia et al., *SEM 2023)

• LEXPLAIN: Improving Model Explanations via Lexicon Supervision (Ahia et al., *SEM 2023)

ACL

• Orevaoghene Ahia, Hila Gonen, Vidhisha Balachandran, Yulia Tsvetkov, and Noah A. Smith. 2023. LEXPLAIN: Improving Model Explanations via Lexicon Supervision. In Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), pages 207–216, Toronto, Canada. Association for Computational Linguistics.