<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="howitt-etal-2024-generalizations">
    <titleInfo>
        <title>Generalizations across filler-gap dependencies in neural language models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Katherine</namePart>
        <namePart type="family">Howitt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sathvik</namePart>
        <namePart type="family">Nair</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Allison</namePart>
        <namePart type="family">Dods</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Robert</namePart>
        <namePart type="given">Melvin</namePart>
        <namePart type="family">Hopkins</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 28th Conference on Computational Natural Language Learning</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Libby</namePart>
            <namePart type="family">Barak</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Malihe</namePart>
            <namePart type="family">Alikhani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, FL, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Humans develop their grammars by making structural generalizations from finite input. We ask how filler-gap dependencies (FGDs), which share a structural generalization despite diverse surface forms, might arise from the input. We explicitly control the input to a neural language model (NLM) to uncover whether the model posits a shared representation for FGDs. We show that while NLMs do have success differentiating grammatical from ungrammatical FGDs, they rely on superficial properties of the input, rather than on a shared generalization. Our work highlights the need for specific linguistic inductive biases to model language acquisition.</abstract>
    <identifier type="citekey">howitt-etal-2024-generalizations</identifier>
    <location>
        <url>https://aclanthology.org/2024.conll-1.21</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>269</start>
            <end>279</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generalizations across filler-gap dependencies in neural language models
%A Howitt, Katherine
%A Nair, Sathvik
%A Dods, Allison
%A Hopkins, Robert Melvin
%Y Barak, Libby
%Y Alikhani, Malihe
%S Proceedings of the 28th Conference on Computational Natural Language Learning
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F howitt-etal-2024-generalizations
%X Humans develop their grammars by making structural generalizations from finite input. We ask how filler-gap dependencies (FGDs), which share a structural generalization despite diverse surface forms, might arise from the input. We explicitly control the input to a neural language model (NLM) to uncover whether the model posits a shared representation for FGDs. We show that while NLMs do have success differentiating grammatical from ungrammatical FGDs, they rely on superficial properties of the input, rather than on a shared generalization. Our work highlights the need for specific linguistic inductive biases to model language acquisition.
%U https://aclanthology.org/2024.conll-1.21
%P 269-279

Markdown (Informal)

[Generalizations across filler-gap dependencies in neural language models](https://aclanthology.org/2024.conll-1.21) (Howitt et al., CoNLL 2024)

• Generalizations across filler-gap dependencies in neural language models (Howitt et al., CoNLL 2024)

ACL

• Katherine Howitt, Sathvik Nair, Allison Dods, and Robert Melvin Hopkins. 2024. Generalizations across filler-gap dependencies in neural language models. In Proceedings of the 28th Conference on Computational Natural Language Learning, pages 269–279, Miami, FL, USA. Association for Computational Linguistics.