<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chinnappa-etal-2019-extracting">
    <titleInfo>
        <title>Extracting Possessions from Social Media: Images Complement Language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dhivya</namePart>
        <namePart type="family">Chinnappa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Srikala</namePart>
        <namePart type="family">Murugan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eduardo</namePart>
        <namePart type="family">Blanco</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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kentaro</namePart>
            <namePart type="family">Inui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jing</namePart>
            <namePart type="family">Jiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vincent</namePart>
            <namePart type="family">Ng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xiaojun</namePart>
            <namePart type="family">Wan</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>This paper describes a new dataset and experiments to determine whether authors of tweets possess the objects they tweet about. We work with 5,000 tweets and show that both humans and neural networks benefit from images in addition to text. We also introduce a simple yet effective strategy to incorporate visual information into any neural network beyond weights from pretrained networks. Specifically, we consider the tags identified in an image as an additional textual input, and leverage pretrained word embeddings as usually done with regular text. Experimental results show this novel strategy is beneficial.</abstract>
    <identifier type="citekey">chinnappa-etal-2019-extracting</identifier>
    <identifier type="doi">10.18653/v1/D19-1061</identifier>
    <location>
        <url>https://aclanthology.org/D19-1061</url>
    </location>
    <part>
        <date>2019-11</date>
        <extent unit="page">
            <start>663</start>
            <end>672</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Extracting Possessions from Social Media: Images Complement Language
%A Chinnappa, Dhivya
%A Murugan, Srikala
%A Blanco, Eduardo
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F chinnappa-etal-2019-extracting
%X This paper describes a new dataset and experiments to determine whether authors of tweets possess the objects they tweet about. We work with 5,000 tweets and show that both humans and neural networks benefit from images in addition to text. We also introduce a simple yet effective strategy to incorporate visual information into any neural network beyond weights from pretrained networks. Specifically, we consider the tags identified in an image as an additional textual input, and leverage pretrained word embeddings as usually done with regular text. Experimental results show this novel strategy is beneficial.
%R 10.18653/v1/D19-1061
%U https://aclanthology.org/D19-1061
%U https://doi.org/10.18653/v1/D19-1061
%P 663-672

Markdown (Informal)

[Extracting Possessions from Social Media: Images Complement Language](https://aclanthology.org/D19-1061) (Chinnappa et al., EMNLP-IJCNLP 2019)

• Extracting Possessions from Social Media: Images Complement Language (Chinnappa et al., EMNLP-IJCNLP 2019)

ACL

• Dhivya Chinnappa, Srikala Murugan, and Eduardo Blanco. 2019. Extracting Possessions from Social Media: Images Complement Language. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 663–672, Hong Kong, China. Association for Computational Linguistics.