<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buch-etal-2021-neural">
    <titleInfo>
        <title>Neural Event Semantics for Grounded Language Understanding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shyamal</namePart>
        <namePart type="family">Buch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Li</namePart>
        <namePart type="family">Fei-Fei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Noah</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">Goodman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding. Our approach treats all words as classifiers that compose to form a sentence meaning by multiplying output scores. These classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention. NES is trainable end-to-end by gradient descent with minimal supervision. We evaluate our method on compositional grounded language tasks in controlled synthetic and real-world settings. NES offers stronger generalization capability than standard function-based compositional frameworks, while improving accuracy over state-of-the-art neural methods on real-world language tasks.</abstract>
    <identifier type="citekey">buch-etal-2021-neural</identifier>
    <identifier type="doi">10.1162/tacl_a_00402</identifier>
    <location>
        <url>https://aclanthology.org/2021.tacl-1.52</url>
    </location>
    <part>
        <date>2021</date>
        <detail type="volume"><number>9</number></detail>
        <extent unit="page">
            <start>875</start>
            <end>890</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Neural Event Semantics for Grounded Language Understanding
%A Buch, Shyamal
%A Fei-Fei, Li
%A Goodman, Noah D.
%J Transactions of the Association for Computational Linguistics
%D 2021
%V 9
%I MIT Press
%C Cambridge, MA
%F buch-etal-2021-neural
%X We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding. Our approach treats all words as classifiers that compose to form a sentence meaning by multiplying output scores. These classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention. NES is trainable end-to-end by gradient descent with minimal supervision. We evaluate our method on compositional grounded language tasks in controlled synthetic and real-world settings. NES offers stronger generalization capability than standard function-based compositional frameworks, while improving accuracy over state-of-the-art neural methods on real-world language tasks.
%R 10.1162/tacl_a_00402
%U https://aclanthology.org/2021.tacl-1.52
%U https://doi.org/10.1162/tacl_a_00402
%P 875-890

Markdown (Informal)

[Neural Event Semantics for Grounded Language Understanding](https://aclanthology.org/2021.tacl-1.52) (Buch et al., TACL 2021)

• Neural Event Semantics for Grounded Language Understanding (Buch et al., TACL 2021)

ACL

• Shyamal Buch, Li Fei-Fei, and Noah D. Goodman. 2021. Neural Event Semantics for Grounded Language Understanding. Transactions of the Association for Computational Linguistics, 9:875–890.