@inproceedings{gu-etal-2018-multimodal,
title = "Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment",
author = "Gu, Yue and
Yang, Kangning and
Fu, Shiyu and
Chen, Shuhong and
Li, Xinyu and
Marsic, Ivan",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1207",
doi = "10.18653/v1/P18-1207",
pages = "2225--2235",
abstract = "Multimodal affective computing, learning to recognize and interpret human affect and subjective information from multiple data sources, is still a challenge because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract levels, ignoring time-dependent interactions between modalities. Addressing such issues, we introduce a hierarchical multimodal architecture with attention and word-level fusion to classify utterance-level sentiment and emotion from text and audio data. Our introduced model outperforms state-of-the-art approaches on published datasets, and we demonstrate that our model is able to visualize and interpret synchronized attention over modalities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2018-multimodal">
<titleInfo>
<title>Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kangning</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiyu</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuhong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Marsic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal affective computing, learning to recognize and interpret human affect and subjective information from multiple data sources, is still a challenge because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract levels, ignoring time-dependent interactions between modalities. Addressing such issues, we introduce a hierarchical multimodal architecture with attention and word-level fusion to classify utterance-level sentiment and emotion from text and audio data. Our introduced model outperforms state-of-the-art approaches on published datasets, and we demonstrate that our model is able to visualize and interpret synchronized attention over modalities.</abstract>
<identifier type="citekey">gu-etal-2018-multimodal</identifier>
<identifier type="doi">10.18653/v1/P18-1207</identifier>
<location>
<url>https://aclanthology.org/P18-1207</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>2225</start>
<end>2235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment
%A Gu, Yue
%A Yang, Kangning
%A Fu, Shiyu
%A Chen, Shuhong
%A Li, Xinyu
%A Marsic, Ivan
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F gu-etal-2018-multimodal
%X Multimodal affective computing, learning to recognize and interpret human affect and subjective information from multiple data sources, is still a challenge because: (i) it is hard to extract informative features to represent human affects from heterogeneous inputs; (ii) current fusion strategies only fuse different modalities at abstract levels, ignoring time-dependent interactions between modalities. Addressing such issues, we introduce a hierarchical multimodal architecture with attention and word-level fusion to classify utterance-level sentiment and emotion from text and audio data. Our introduced model outperforms state-of-the-art approaches on published datasets, and we demonstrate that our model is able to visualize and interpret synchronized attention over modalities.
%R 10.18653/v1/P18-1207
%U https://aclanthology.org/P18-1207
%U https://doi.org/10.18653/v1/P18-1207
%P 2225-2235
Markdown (Informal)
[Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment](https://aclanthology.org/P18-1207) (Gu et al., ACL 2018)
ACL