<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jian-reddy-2023-syntactic">
    <titleInfo>
        <title>Syntactic Substitutability as Unsupervised Dependency Syntax</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jasper</namePart>
        <namePart type="family">Jian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Siva</namePart>
        <namePart type="family">Reddy</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 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</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>Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. In this work, we explore the hypothesis that syntactic dependencies can be represented in language model attention distributions and propose a new method to induce these structures theory-agnostically. Instead of modeling syntactic relations as defined by annotation schemata, we model a more general property implicit in the definition of dependency relations, syntactic substitutability. This property captures the fact that words at either end of a dependency can be substituted with words from the same category. Substitutions can be used to generate a set of syntactically invariant sentences whose representations are then used for parsing. We show that increasing the number of substitutions used improves parsing accuracy on natural data. On long-distance subject-verb agreement constructions, our method achieves 79.5% recall compared to 8.9% using a previous method. Our method also provides improvements when transferred to a different parsing setup, demonstrating that it generalizes.</abstract>
    <identifier type="citekey">jian-reddy-2023-syntactic</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.144</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.144</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>2341</start>
            <end>2360</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Syntactic Substitutability as Unsupervised Dependency Syntax
%A Jian, Jasper
%A Reddy, Siva
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F jian-reddy-2023-syntactic
%X Syntax is a latent hierarchical structure which underpins the robust and compositional nature of human language. In this work, we explore the hypothesis that syntactic dependencies can be represented in language model attention distributions and propose a new method to induce these structures theory-agnostically. Instead of modeling syntactic relations as defined by annotation schemata, we model a more general property implicit in the definition of dependency relations, syntactic substitutability. This property captures the fact that words at either end of a dependency can be substituted with words from the same category. Substitutions can be used to generate a set of syntactically invariant sentences whose representations are then used for parsing. We show that increasing the number of substitutions used improves parsing accuracy on natural data. On long-distance subject-verb agreement constructions, our method achieves 79.5% recall compared to 8.9% using a previous method. Our method also provides improvements when transferred to a different parsing setup, demonstrating that it generalizes.
%R 10.18653/v1/2023.emnlp-main.144
%U https://aclanthology.org/2023.emnlp-main.144
%U https://doi.org/10.18653/v1/2023.emnlp-main.144
%P 2341-2360

Markdown (Informal)

[Syntactic Substitutability as Unsupervised Dependency Syntax](https://aclanthology.org/2023.emnlp-main.144) (Jian & Reddy, EMNLP 2023)

• Syntactic Substitutability as Unsupervised Dependency Syntax (Jian & Reddy, EMNLP 2023)

ACL

• Jasper Jian and Siva Reddy. 2023. Syntactic Substitutability as Unsupervised Dependency Syntax. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2341–2360, Singapore. Association for Computational Linguistics.