<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beard-etal-2018-multi">
    <titleInfo>
        <title>Multi-Modal Sequence Fusion via Recursive Attention for Emotion Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rory</namePart>
        <namePart type="family">Beard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ritwik</namePart>
        <namePart type="family">Das</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raymond</namePart>
        <namePart type="given">W</namePart>
        <namePart type="given">M</namePart>
        <namePart type="family">Ng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">P</namePart>
        <namePart type="given">G</namePart>
        <namePart type="given">Keerthana</namePart>
        <namePart type="family">Gopalakrishnan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luka</namePart>
        <namePart type="family">Eerens</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pawel</namePart>
        <namePart type="family">Swietojanski</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ondrej</namePart>
        <namePart type="family">Miksik</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd Conference on Computational Natural Language Learning</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="family">Titov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Natural human communication is nuanced and inherently multi-modal. Humans possess specialised sensoria for processing vocal, visual, and linguistic, and para-linguistic information, but form an intricately fused percept of the multi-modal data stream to provide a holistic representation. Analysis of emotional content in face-to-face communication is a cognitive task to which humans are particularly attuned, given its sociological importance, and poses a difficult challenge for machine emulation due to the subtlety and expressive variability of cross-modal cues. Inspired by the empirical success of recent so-called End-To-End Memory Networks and related works, we propose an approach based on recursive multi-attention with a shared external memory updated over multiple gated iterations of analysis. We evaluate our model across several large multi-modal datasets and show that global contextualised memory with gated memory update can effectively achieve emotion recognition.</abstract>
    <identifier type="citekey">beard-etal-2018-multi</identifier>
    <identifier type="doi">10.18653/v1/K18-1025</identifier>
    <location>
        <url>https://aclanthology.org/K18-1025</url>
    </location>
    <part>
        <date>2018-10</date>
        <extent unit="page">
            <start>251</start>
            <end>259</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Modal Sequence Fusion via Recursive Attention for Emotion Recognition
%A Beard, Rory
%A Das, Ritwik
%A Ng, Raymond W. M.
%A Gopalakrishnan, P. G. Keerthana
%A Eerens, Luka
%A Swietojanski, Pawel
%A Miksik, Ondrej
%Y Korhonen, Anna
%Y Titov, Ivan
%S Proceedings of the 22nd Conference on Computational Natural Language Learning
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F beard-etal-2018-multi
%X Natural human communication is nuanced and inherently multi-modal. Humans possess specialised sensoria for processing vocal, visual, and linguistic, and para-linguistic information, but form an intricately fused percept of the multi-modal data stream to provide a holistic representation. Analysis of emotional content in face-to-face communication is a cognitive task to which humans are particularly attuned, given its sociological importance, and poses a difficult challenge for machine emulation due to the subtlety and expressive variability of cross-modal cues. Inspired by the empirical success of recent so-called End-To-End Memory Networks and related works, we propose an approach based on recursive multi-attention with a shared external memory updated over multiple gated iterations of analysis. We evaluate our model across several large multi-modal datasets and show that global contextualised memory with gated memory update can effectively achieve emotion recognition.
%R 10.18653/v1/K18-1025
%U https://aclanthology.org/K18-1025
%U https://doi.org/10.18653/v1/K18-1025
%P 251-259

Markdown (Informal)

[Multi-Modal Sequence Fusion via Recursive Attention for Emotion Recognition](https://aclanthology.org/K18-1025) (Beard et al., CoNLL 2018)

• Multi-Modal Sequence Fusion via Recursive Attention for Emotion Recognition (Beard et al., CoNLL 2018)

ACL

• Rory Beard, Ritwik Das, Raymond W. M. Ng, P. G. Keerthana Gopalakrishnan, Luka Eerens, Pawel Swietojanski, and Ondrej Miksik. 2018. Multi-Modal Sequence Fusion via Recursive Attention for Emotion Recognition. In Proceedings of the 22nd Conference on Computational Natural Language Learning, pages 251–259, Brussels, Belgium. Association for Computational Linguistics.