<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-srikumar-2023-metaprobe">
    <titleInfo>
        <title>METAPROBE: A Representation- and Task-Agnostic Probe</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yichu</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vivek</namePart>
        <namePart type="family">Srikumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yonatan</namePart>
            <namePart type="family">Belinkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sophie</namePart>
            <namePart type="family">Hao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jaap</namePart>
            <namePart type="family">Jumelet</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Najoung</namePart>
            <namePart type="family">Kim</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Arya</namePart>
            <namePart type="family">McCarthy</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hosein</namePart>
            <namePart type="family">Mohebbi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Probing contextualized representations typically involves comparing task-specific model predictions against ground truth linguistic labels. Although this methodology shows what information can be recovered by a classifier, it does not reveal how a classifier uses the representation to make its decision. To address the latter problem, we ask: Do task-classifiers rely on representation- and task-independent geometric patterns in the embedding space? We explore this question by developing MetaProbe, an approach that uses geometric properties of representations to predict the behavior of task-specific classifiers (i.e., their predictions as opposed to the ground truth). Our experiments reveal the existence of universal geometric patterns across representations that can predict classifier predictions. Consequently, this allows us to posit a geometric explanation for the impressive performance of contextualized representations.</abstract>
    <identifier type="citekey">zhou-srikumar-2023-metaprobe</identifier>
    <identifier type="doi">10.18653/v1/2023.blackboxnlp-1.18</identifier>
    <location>
        <url>https://aclanthology.org/2023.blackboxnlp-1.18</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>233</start>
            <end>249</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T METAPROBE: A Representation- and Task-Agnostic Probe
%A Zhou, Yichu
%A Srikumar, Vivek
%Y Belinkov, Yonatan
%Y Hao, Sophie
%Y Jumelet, Jaap
%Y Kim, Najoung
%Y McCarthy, Arya
%Y Mohebbi, Hosein
%S Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhou-srikumar-2023-metaprobe
%X Probing contextualized representations typically involves comparing task-specific model predictions against ground truth linguistic labels. Although this methodology shows what information can be recovered by a classifier, it does not reveal how a classifier uses the representation to make its decision. To address the latter problem, we ask: Do task-classifiers rely on representation- and task-independent geometric patterns in the embedding space? We explore this question by developing MetaProbe, an approach that uses geometric properties of representations to predict the behavior of task-specific classifiers (i.e., their predictions as opposed to the ground truth). Our experiments reveal the existence of universal geometric patterns across representations that can predict classifier predictions. Consequently, this allows us to posit a geometric explanation for the impressive performance of contextualized representations.
%R 10.18653/v1/2023.blackboxnlp-1.18
%U https://aclanthology.org/2023.blackboxnlp-1.18
%U https://doi.org/10.18653/v1/2023.blackboxnlp-1.18
%P 233-249

Markdown (Informal)

[METAPROBE: A Representation- and Task-Agnostic Probe](https://aclanthology.org/2023.blackboxnlp-1.18) (Zhou & Srikumar, BlackboxNLP-WS 2023)

• METAPROBE: A Representation- and Task-Agnostic Probe (Zhou & Srikumar, BlackboxNLP-WS 2023)

ACL

• Yichu Zhou and Vivek Srikumar. 2023. METAPROBE: A Representation- and Task-Agnostic Probe. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 233–249, Singapore. Association for Computational Linguistics.