@inproceedings{yang-etal-2021-mtag,
title = "{MTAG}: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences",
author = "Yang, Jianing and
Wang, Yongxin and
Yi, Ruitao and
Zhu, Yuying and
Rehman, Azaan and
Zadeh, Amir and
Poria, Soujanya and
Morency, Louis-Philippe",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.79",
doi = "10.18653/v1/2021.naacl-main.79",
pages = "1009--1021",
abstract = "Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in this domain exhibits complex multi-relational and temporal interactions. Learning from this data is a fundamentally challenging research problem. In this paper, we propose Modal-Temporal Attention Graph (MTAG). MTAG is an interpretable graph-based neural model that provides a suitable framework for analyzing multimodal sequential data. We first introduce a procedure to convert unaligned multimodal sequence data into a graph with heterogeneous nodes and edges that captures the rich interactions across modalities and through time. Then, a novel graph fusion operation, called MTAG fusion, along with a dynamic pruning and read-out technique, is designed to efficiently process this modal-temporal graph and capture various interactions. By learning to focus only on the important interactions within the graph, MTAG achieves state-of-the-art performance on multimodal sentiment analysis and emotion recognition benchmarks, while utilizing significantly fewer model parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-mtag">
<titleInfo>
<title>MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruitao</namePart>
<namePart type="family">Yi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuying</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azaan</namePart>
<namePart type="family">Rehman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in this domain exhibits complex multi-relational and temporal interactions. Learning from this data is a fundamentally challenging research problem. In this paper, we propose Modal-Temporal Attention Graph (MTAG). MTAG is an interpretable graph-based neural model that provides a suitable framework for analyzing multimodal sequential data. We first introduce a procedure to convert unaligned multimodal sequence data into a graph with heterogeneous nodes and edges that captures the rich interactions across modalities and through time. Then, a novel graph fusion operation, called MTAG fusion, along with a dynamic pruning and read-out technique, is designed to efficiently process this modal-temporal graph and capture various interactions. By learning to focus only on the important interactions within the graph, MTAG achieves state-of-the-art performance on multimodal sentiment analysis and emotion recognition benchmarks, while utilizing significantly fewer model parameters.</abstract>
<identifier type="citekey">yang-etal-2021-mtag</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.79</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.79</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1009</start>
<end>1021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences
%A Yang, Jianing
%A Wang, Yongxin
%A Yi, Ruitao
%A Zhu, Yuying
%A Rehman, Azaan
%A Zadeh, Amir
%A Poria, Soujanya
%A Morency, Louis-Philippe
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F yang-etal-2021-mtag
%X Human communication is multimodal in nature; it is through multiple modalities such as language, voice, and facial expressions, that opinions and emotions are expressed. Data in this domain exhibits complex multi-relational and temporal interactions. Learning from this data is a fundamentally challenging research problem. In this paper, we propose Modal-Temporal Attention Graph (MTAG). MTAG is an interpretable graph-based neural model that provides a suitable framework for analyzing multimodal sequential data. We first introduce a procedure to convert unaligned multimodal sequence data into a graph with heterogeneous nodes and edges that captures the rich interactions across modalities and through time. Then, a novel graph fusion operation, called MTAG fusion, along with a dynamic pruning and read-out technique, is designed to efficiently process this modal-temporal graph and capture various interactions. By learning to focus only on the important interactions within the graph, MTAG achieves state-of-the-art performance on multimodal sentiment analysis and emotion recognition benchmarks, while utilizing significantly fewer model parameters.
%R 10.18653/v1/2021.naacl-main.79
%U https://aclanthology.org/2021.naacl-main.79
%U https://doi.org/10.18653/v1/2021.naacl-main.79
%P 1009-1021
Markdown (Informal)
[MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences](https://aclanthology.org/2021.naacl-main.79) (Yang et al., NAACL 2021)
ACL