<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seyffarth-etal-2021-implicit">
    <titleInfo>
        <title>Implicit representations of event properties within contextual language models: Searching for “causativity neurons”</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Esther</namePart>
        <namePart type="family">Seyffarth</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Younes</namePart>
        <namePart type="family">Samih</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Laura</namePart>
        <namePart type="family">Kallmeyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hassan</namePart>
        <namePart type="family">Sajjad</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 14th International Conference on Computational Semantics (IWCS)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sina</namePart>
            <namePart type="family">Zarrieß</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Johan</namePart>
            <namePart type="family">Bos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rik</namePart>
            <namePart type="family">van Noord</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lasha</namePart>
            <namePart type="family">Abzianidze</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Groningen, The Netherlands (online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper addresses the question to which extent neural contextual language models such as BERT implicitly represent complex semantic properties. More concretely, the paper shows that the neuron activations obtained from processing an English sentence provide discriminative features for predicting the (non-)causativity of the event denoted by the verb in a simple linear classifier. A layer-wise analysis reveals that the relevant properties are mostly learned in the higher layers. Moreover, further experiments show that appr. 10% of the neuron activations are enough to already predict causativity with a relatively high accuracy.</abstract>
    <identifier type="citekey">seyffarth-etal-2021-implicit</identifier>
    <location>
        <url>https://aclanthology.org/2021.iwcs-1.11</url>
    </location>
    <part>
        <date>2021-06</date>
        <extent unit="page">
            <start>110</start>
            <end>120</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Implicit representations of event properties within contextual language models: Searching for “causativity neurons”
%A Seyffarth, Esther
%A Samih, Younes
%A Kallmeyer, Laura
%A Sajjad, Hassan
%Y Zarrieß, Sina
%Y Bos, Johan
%Y van Noord, Rik
%Y Abzianidze, Lasha
%S Proceedings of the 14th International Conference on Computational Semantics (IWCS)
%D 2021
%8 June
%I Association for Computational Linguistics
%C Groningen, The Netherlands (online)
%F seyffarth-etal-2021-implicit
%X This paper addresses the question to which extent neural contextual language models such as BERT implicitly represent complex semantic properties. More concretely, the paper shows that the neuron activations obtained from processing an English sentence provide discriminative features for predicting the (non-)causativity of the event denoted by the verb in a simple linear classifier. A layer-wise analysis reveals that the relevant properties are mostly learned in the higher layers. Moreover, further experiments show that appr. 10% of the neuron activations are enough to already predict causativity with a relatively high accuracy.
%U https://aclanthology.org/2021.iwcs-1.11
%P 110-120

Markdown (Informal)

[Implicit representations of event properties within contextual language models: Searching for “causativity neurons”](https://aclanthology.org/2021.iwcs-1.11) (Seyffarth et al., IWCS 2021)

• Implicit representations of event properties within contextual language models: Searching for “causativity neurons” (Seyffarth et al., IWCS 2021)

ACL

• Esther Seyffarth, Younes Samih, Laura Kallmeyer, and Hassan Sajjad. 2021. Implicit representations of event properties within contextual language models: Searching for “causativity neurons”. In Proceedings of the 14th International Conference on Computational Semantics (IWCS), pages 110–120, Groningen, The Netherlands (online). Association for Computational Linguistics.