<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tucker-etal-2022-syntax">
    <titleInfo>
        <title>When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mycal</namePart>
        <namePart type="family">Tucker</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tiwalayo</namePart>
        <namePart type="family">Eisape</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Peng</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roger</namePart>
        <namePart type="family">Levy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Julie</namePart>
        <namePart type="family">Shah</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="given">Vladimir</namePart>
            <namePart type="family">Meza Ruiz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield “false negative” causality results: models may use representations of syntax, but probes may have learned to use redundant encodings of the same syntactic information. We demonstrate that models do encode syntactic information redundantly and introduce a new probe design that guides probes to consider all syntactic information present in embeddings. Using these probes, we find evidence for the use of syntax in models where prior methods did not, allowing us to boost model performance by injecting syntactic information into representations.</abstract>
    <identifier type="citekey">tucker-etal-2022-syntax</identifier>
    <identifier type="doi">10.18653/v1/2022.naacl-main.394</identifier>
    <location>
        <url>https://aclanthology.org/2022.naacl-main.394</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>5393</start>
            <end>5408</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
%A Tucker, Mycal
%A Eisape, Tiwalayo
%A Qian, Peng
%A Levy, Roger
%A Shah, Julie
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F tucker-etal-2022-syntax
%X Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield “false negative” causality results: models may use representations of syntax, but probes may have learned to use redundant encodings of the same syntactic information. We demonstrate that models do encode syntactic information redundantly and introduce a new probe design that guides probes to consider all syntactic information present in embeddings. Using these probes, we find evidence for the use of syntax in models where prior methods did not, allowing us to boost model performance by injecting syntactic information into representations.
%R 10.18653/v1/2022.naacl-main.394
%U https://aclanthology.org/2022.naacl-main.394
%U https://doi.org/10.18653/v1/2022.naacl-main.394
%P 5393-5408

Markdown (Informal)

[When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes](https://aclanthology.org/2022.naacl-main.394) (Tucker et al., NAACL 2022)

• When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes (Tucker et al., NAACL 2022)

ACL

• Mycal Tucker, Tiwalayo Eisape, Peng Qian, Roger Levy, and Julie Shah. 2022. When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5393–5408, Seattle, United States. Association for Computational Linguistics.