<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prasad-etal-2019-using">
    <titleInfo>
        <title>Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Grusha</namePart>
        <namePart type="family">Prasad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marten</namePart>
        <namePart type="family">van Schijndel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tal</namePart>
        <namePart type="family">Linzen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable such success. By establishing a gradient similarity metric between structures, this technique allows us to reconstruct the organization of the LMs’ syntactic representational space. We use this technique to demonstrate that LSTM LMs’ representations of different types of sentences with relative clauses are organized hierarchically in a linguistically interpretable manner, suggesting that the LMs track abstract properties of the sentence.</abstract>
    <identifier type="citekey">prasad-etal-2019-using</identifier>
    <identifier type="doi">10.18653/v1/K19-1007</identifier>
    <location>
        <url>https://aclanthology.org/K19-1007</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>66</start>
            <end>76</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models
%A Prasad, Grusha
%A van Schijndel, Marten
%A Linzen, Tal
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F prasad-etal-2019-using
%X Neural language models (LMs) perform well on tasks that require sensitivity to syntactic structure. Drawing on the syntactic priming paradigm from psycholinguistics, we propose a novel technique to analyze the representations that enable such success. By establishing a gradient similarity metric between structures, this technique allows us to reconstruct the organization of the LMs’ syntactic representational space. We use this technique to demonstrate that LSTM LMs’ representations of different types of sentences with relative clauses are organized hierarchically in a linguistically interpretable manner, suggesting that the LMs track abstract properties of the sentence.
%R 10.18653/v1/K19-1007
%U https://aclanthology.org/K19-1007
%U https://doi.org/10.18653/v1/K19-1007
%P 66-76

Markdown (Informal)

[Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models](https://aclanthology.org/K19-1007) (Prasad et al., CoNLL 2019)

• Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models (Prasad et al., CoNLL 2019)

ACL

• Grusha Prasad, Marten van Schijndel, and Tal Linzen. 2019. Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 66–76, Hong Kong, China. Association for Computational Linguistics.