@inproceedings{sikos-pado-2019-frame,
    title = "Frame Identification as Categorization: Exemplars vs Prototypes in Embeddingland",
    author = "Sikos, Jennifer  and
      Pad{\'o}, Sebastian",
    editor = "Dobnik, Simon  and
      Chatzikyriakidis, Stergios  and
      Demberg, Vera",
    booktitle = "Proceedings of the 13th International Conference on Computational Semantics - Long Papers",
    month = may,
    year = "2019",
    address = "Gothenburg, Sweden",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W19-0425/",
    doi = "10.18653/v1/W19-0425",
    pages = "295--306",
    abstract = "Categorization is a central capability of human cognition, and a number of theories have been developed to account for properties of categorization. Even though many tasks in semantics also involve categorization of some kind, theories of categorization do not play a major role in contemporary research in computational linguistics. This paper follows the idea that embedding-based models of semantics lend themselves well to being formulated in terms of classical categorization theories. The benefit is a space of model families that enables (a) the formulation of hypotheses about the impact of major design decisions, and (b) a transparent assessment of these decisions. We instantiate this idea on the task of frame-semantic frame identification. We define four models that cross two design variables: (a) the choice of prototype vs. exemplar categorization, corresponding to different degrees of generalization applied to the input; and (b) the presence vs. absence of a fine-tuning step, corresponding to generic vs. task-adaptive categorization. We find that for frame identification, generalization and task-adaptive categorization both yield substantial benefits. Our prototype-based, fine-tuned model, which combines the best choices for these variables, establishes a new state of the art in frame identification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sikos-pado-2019-frame">
    <titleInfo>
        <title>Frame Identification as Categorization: Exemplars vs Prototypes in Embeddingland</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jennifer</namePart>
        <namePart type="family">Sikos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sebastian</namePart>
        <namePart type="family">Padó</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 13th International Conference on Computational Semantics - Long Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Dobnik</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stergios</namePart>
            <namePart type="family">Chatzikyriakidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vera</namePart>
            <namePart type="family">Demberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gothenburg, Sweden</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Categorization is a central capability of human cognition, and a number of theories have been developed to account for properties of categorization. Even though many tasks in semantics also involve categorization of some kind, theories of categorization do not play a major role in contemporary research in computational linguistics. This paper follows the idea that embedding-based models of semantics lend themselves well to being formulated in terms of classical categorization theories. The benefit is a space of model families that enables (a) the formulation of hypotheses about the impact of major design decisions, and (b) a transparent assessment of these decisions. We instantiate this idea on the task of frame-semantic frame identification. We define four models that cross two design variables: (a) the choice of prototype vs. exemplar categorization, corresponding to different degrees of generalization applied to the input; and (b) the presence vs. absence of a fine-tuning step, corresponding to generic vs. task-adaptive categorization. We find that for frame identification, generalization and task-adaptive categorization both yield substantial benefits. Our prototype-based, fine-tuned model, which combines the best choices for these variables, establishes a new state of the art in frame identification.</abstract>
    <identifier type="citekey">sikos-pado-2019-frame</identifier>
    <identifier type="doi">10.18653/v1/W19-0425</identifier>
    <location>
        <url>https://aclanthology.org/W19-0425/</url>
    </location>
    <part>
        <date>2019-05</date>
        <extent unit="page">
            <start>295</start>
            <end>306</end>
        </extent>
    </part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Frame Identification as Categorization: Exemplars vs Prototypes in Embeddingland
%A Sikos, Jennifer
%A Padó, Sebastian
%Y Dobnik, Simon
%Y Chatzikyriakidis, Stergios
%Y Demberg, Vera
%S Proceedings of the 13th International Conference on Computational Semantics - Long Papers
%D 2019
%8 May
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F sikos-pado-2019-frame
%X Categorization is a central capability of human cognition, and a number of theories have been developed to account for properties of categorization. Even though many tasks in semantics also involve categorization of some kind, theories of categorization do not play a major role in contemporary research in computational linguistics. This paper follows the idea that embedding-based models of semantics lend themselves well to being formulated in terms of classical categorization theories. The benefit is a space of model families that enables (a) the formulation of hypotheses about the impact of major design decisions, and (b) a transparent assessment of these decisions. We instantiate this idea on the task of frame-semantic frame identification. We define four models that cross two design variables: (a) the choice of prototype vs. exemplar categorization, corresponding to different degrees of generalization applied to the input; and (b) the presence vs. absence of a fine-tuning step, corresponding to generic vs. task-adaptive categorization. We find that for frame identification, generalization and task-adaptive categorization both yield substantial benefits. Our prototype-based, fine-tuned model, which combines the best choices for these variables, establishes a new state of the art in frame identification.
%R 10.18653/v1/W19-0425
%U https://aclanthology.org/W19-0425/
%U https://doi.org/10.18653/v1/W19-0425
%P 295-306
Markdown (Informal)
[Frame Identification as Categorization: Exemplars vs Prototypes in Embeddingland](https://aclanthology.org/W19-0425/) (Sikos & Padó, IWCS 2019)
ACL