<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahay-etal-2020-low">
    <titleInfo>
        <title>Low Rank Fusion based Transformers for Multimodal Sequences</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Saurav</namePart>
        <namePart type="family">Sahay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eda</namePart>
        <namePart type="family">Okur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shachi</namePart>
        <namePart type="family">H Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lama</namePart>
        <namePart type="family">Nachman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Amir</namePart>
            <namePart type="family">Zadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Louis-Philippe</namePart>
            <namePart type="family">Morency</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Paul</namePart>
            <namePart type="given">Pu</namePart>
            <namePart type="family">Liang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Soujanya</namePart>
            <namePart type="family">Poria</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Our senses individually work in a coordinated fashion to express our emotional intentions. In this work, we experiment with modeling modality-specific sensory signals to attend to our latent multimodal emotional intentions and vice versa expressed via low-rank multimodal fusion and multimodal transformers. The low-rank factorization of multimodal fusion amongst the modalities helps represent approximate multiplicative latent signal interactions. Motivated by the work of (CITATION) and (CITATION), we present our transformer-based cross-fusion architecture without any over-parameterization of the model. The low-rank fusion helps represent the latent signal interactions while the modality-specific attention helps focus on relevant parts of the signal. We present two methods for the Multimodal Sentiment and Emotion Recognition results on CMU-MOSEI, CMU-MOSI, and IEMOCAP datasets and show that our models have lesser parameters, train faster and perform comparably to many larger fusion-based architectures.</abstract>
    <identifier type="citekey">sahay-etal-2020-low</identifier>
    <identifier type="doi">10.18653/v1/2020.challengehml-1.4</identifier>
    <location>
        <url>https://aclanthology.org/2020.challengehml-1.4/</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>29</start>
            <end>34</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Low Rank Fusion based Transformers for Multimodal Sequences
%A Sahay, Saurav
%A Okur, Eda
%A H Kumar, Shachi
%A Nachman, Lama
%Y Zadeh, Amir
%Y Morency, Louis-Philippe
%Y Liang, Paul Pu
%Y Poria, Soujanya
%S Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F sahay-etal-2020-low
%X Our senses individually work in a coordinated fashion to express our emotional intentions. In this work, we experiment with modeling modality-specific sensory signals to attend to our latent multimodal emotional intentions and vice versa expressed via low-rank multimodal fusion and multimodal transformers. The low-rank factorization of multimodal fusion amongst the modalities helps represent approximate multiplicative latent signal interactions. Motivated by the work of (CITATION) and (CITATION), we present our transformer-based cross-fusion architecture without any over-parameterization of the model. The low-rank fusion helps represent the latent signal interactions while the modality-specific attention helps focus on relevant parts of the signal. We present two methods for the Multimodal Sentiment and Emotion Recognition results on CMU-MOSEI, CMU-MOSI, and IEMOCAP datasets and show that our models have lesser parameters, train faster and perform comparably to many larger fusion-based architectures.
%R 10.18653/v1/2020.challengehml-1.4
%U https://aclanthology.org/2020.challengehml-1.4/
%U https://doi.org/10.18653/v1/2020.challengehml-1.4
%P 29-34

Markdown (Informal)

[Low Rank Fusion based Transformers for Multimodal Sequences](https://aclanthology.org/2020.challengehml-1.4/) (Sahay et al., Challenge-HML 2020)

• Low Rank Fusion based Transformers for Multimodal Sequences (Sahay et al., Challenge-HML 2020)

ACL

• Saurav Sahay, Eda Okur, Shachi H Kumar, and Lama Nachman. 2020. Low Rank Fusion based Transformers for Multimodal Sequences. In Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML), pages 29–34, Seattle, USA. Association for Computational Linguistics.