<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="proietti-etal-2022-bert">
    <titleInfo>
        <title>Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mattia</namePart>
        <namePart type="family">Proietti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gianluca</namePart>
        <namePart type="family">Lebani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alessandro</namePart>
        <namePart type="family">Lenci</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 29th International Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence. Such models have been shown to achieve a state-of-the-art performance on a wide variety of tasks. Yet, the community struggles in understanding what kind of semantic knowledge these representations encode. We report a series of experiments aimed at investigating to what extent one of such models, BERT, is able to infer the semantic relations that, according to Dowty’s Proto-Roles theory, a verbal argument receives by virtue of its role in the event described by the verb. This hypothesis were put to test by learning a linear mapping from the BERT’s verb embeddings to an interpretable space of semantic properties built from the linguistic dataset by White et al. (2016). In a first experiment we tested whether the semantic properties inferred from a typed version of the BERT embeddings would be more linguistically plausible than those produced by relying on static embeddings. We then move to evaluate the semantic properties inferred from the contextual embeddings both against those available in the original dataset, as well as by assessing their ability to model the semantic properties possessed by the agent of the verbs participating in the so-called causative alternation.</abstract>
    <identifier type="citekey">proietti-etal-2022-bert</identifier>
    <location>
        <url>https://aclanthology.org/2022.coling-1.360</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>4101</start>
            <end>4112</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings
%A Proietti, Mattia
%A Lebani, Gianluca
%A Lenci, Alessandro
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F proietti-etal-2022-bert
%X Contextual embeddings build multidimensional representations of word tokens based on their context of occurrence. Such models have been shown to achieve a state-of-the-art performance on a wide variety of tasks. Yet, the community struggles in understanding what kind of semantic knowledge these representations encode. We report a series of experiments aimed at investigating to what extent one of such models, BERT, is able to infer the semantic relations that, according to Dowty’s Proto-Roles theory, a verbal argument receives by virtue of its role in the event described by the verb. This hypothesis were put to test by learning a linear mapping from the BERT’s verb embeddings to an interpretable space of semantic properties built from the linguistic dataset by White et al. (2016). In a first experiment we tested whether the semantic properties inferred from a typed version of the BERT embeddings would be more linguistically plausible than those produced by relying on static embeddings. We then move to evaluate the semantic properties inferred from the contextual embeddings both against those available in the original dataset, as well as by assessing their ability to model the semantic properties possessed by the agent of the verbs participating in the so-called causative alternation.
%U https://aclanthology.org/2022.coling-1.360
%P 4101-4112

Markdown (Informal)

[Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings](https://aclanthology.org/2022.coling-1.360) (Proietti et al., COLING 2022)

• Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings (Proietti et al., COLING 2022)

ACL

• Mattia Proietti, Gianluca Lebani, and Alessandro Lenci. 2022. Does BERT Recognize an Agent? Modeling Dowty’s Proto-Roles with Contextual Embeddings. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4101–4112, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.