<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goel-etal-2019-pre">
    <titleInfo>
        <title>How Pre-trained Word Representations Capture Commonsense Physical Comparisons</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pranav</namePart>
        <namePart type="family">Goel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shi</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jordan</namePart>
        <namePart type="family">Boyd-Graber</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Ostermann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sheng</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Michael</namePart>
            <namePart type="family">Roth</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Peter</namePart>
            <namePart type="family">Clark</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Understanding common sense is important for effective natural language reasoning. One type of common sense is how two objects compare on physical properties such as size and weight: e.g., ‘is a house bigger than a person?’. We probe whether pre-trained representations capture comparisons and find they, in fact, have higher accuracy than previous approaches. They also generalize to comparisons involving objects not seen during training. We investigate how such comparisons are made: models learn a consistent ordering over all the objects in the comparisons. Probing models have significantly higher accuracy than those baseline models which use dataset artifacts: e.g., memorizing some words are larger than any other word.</abstract>
    <identifier type="citekey">goel-etal-2019-pre</identifier>
    <identifier type="doi">10.18653/v1/D19-6016</identifier>
    <location>
        <url>https://aclanthology.org/D19-6016</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>130</start>
            <end>135</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T How Pre-trained Word Representations Capture Commonsense Physical Comparisons
%A Goel, Pranav
%A Feng, Shi
%A Boyd-Graber, Jordan
%Y Ostermann, Simon
%Y Zhang, Sheng
%Y Roth, Michael
%Y Clark, Peter
%S Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F goel-etal-2019-pre
%X Understanding common sense is important for effective natural language reasoning. One type of common sense is how two objects compare on physical properties such as size and weight: e.g., ‘is a house bigger than a person?’. We probe whether pre-trained representations capture comparisons and find they, in fact, have higher accuracy than previous approaches. They also generalize to comparisons involving objects not seen during training. We investigate how such comparisons are made: models learn a consistent ordering over all the objects in the comparisons. Probing models have significantly higher accuracy than those baseline models which use dataset artifacts: e.g., memorizing some words are larger than any other word.
%R 10.18653/v1/D19-6016
%U https://aclanthology.org/D19-6016
%U https://doi.org/10.18653/v1/D19-6016
%P 130-135

Markdown (Informal)

[How Pre-trained Word Representations Capture Commonsense Physical Comparisons](https://aclanthology.org/D19-6016) (Goel et al., 2019)

• How Pre-trained Word Representations Capture Commonsense Physical Comparisons (Goel et al., 2019)

ACL

• Pranav Goel, Shi Feng, and Jordan Boyd-Graber. 2019. How Pre-trained Word Representations Capture Commonsense Physical Comparisons. In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pages 130–135, Hong Kong, China. Association for Computational Linguistics.