@inproceedings{dai-etal-2021-multimodal,
title = "Multimodal End-to-End Sparse Model for Emotion Recognition",
author = "Dai, Wenliang and
Cahyawijaya, Samuel and
Liu, Zihan and
Fung, Pascale",
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.417",
doi = "10.18653/v1/2021.naacl-main.417",
pages = "5305--5316",
abstract = "Existing works in multimodal affective computing tasks, such as emotion recognition and personality recognition, generally adopt a two-phase pipeline by first extracting feature representations for each single modality with hand crafted algorithms, and then performing end-to-end learning with extracted features. However, the extracted features are fixed and cannot be further fine-tuned on different target tasks, and manually finding feature extracting algorithms does not generalize or scale well to different tasks, which can lead to sub-optimal performance. In this paper, we develop a fully end-to-end model that connects the two phases and optimizes them jointly. In addition, we restructure the current datasets to enable the fully end-to-end training. Furthermore, to reduce the computational overhead brought by the end-to-end model, we introduce a sparse cross-modal attention mechanism for the feature extraction. Experimental results show that our fully end-to-end model significantly surpasses the current state-of-the-art models based on the two-phase pipeline. Moreover, by adding the sparse cross-modal attention, our model can maintain the performance with around half less computation in the feature extraction part of the model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-etal-2021-multimodal">
<titleInfo>
<title>Multimodal End-to-End Sparse Model for Emotion Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenliang</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zihan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</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>Existing works in multimodal affective computing tasks, such as emotion recognition and personality recognition, generally adopt a two-phase pipeline by first extracting feature representations for each single modality with hand crafted algorithms, and then performing end-to-end learning with extracted features. However, the extracted features are fixed and cannot be further fine-tuned on different target tasks, and manually finding feature extracting algorithms does not generalize or scale well to different tasks, which can lead to sub-optimal performance. In this paper, we develop a fully end-to-end model that connects the two phases and optimizes them jointly. In addition, we restructure the current datasets to enable the fully end-to-end training. Furthermore, to reduce the computational overhead brought by the end-to-end model, we introduce a sparse cross-modal attention mechanism for the feature extraction. Experimental results show that our fully end-to-end model significantly surpasses the current state-of-the-art models based on the two-phase pipeline. Moreover, by adding the sparse cross-modal attention, our model can maintain the performance with around half less computation in the feature extraction part of the model.</abstract>
<identifier type="citekey">dai-etal-2021-multimodal</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.417</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.417</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5305</start>
<end>5316</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal End-to-End Sparse Model for Emotion Recognition
%A Dai, Wenliang
%A Cahyawijaya, Samuel
%A Liu, Zihan
%A Fung, Pascale
%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 dai-etal-2021-multimodal
%X Existing works in multimodal affective computing tasks, such as emotion recognition and personality recognition, generally adopt a two-phase pipeline by first extracting feature representations for each single modality with hand crafted algorithms, and then performing end-to-end learning with extracted features. However, the extracted features are fixed and cannot be further fine-tuned on different target tasks, and manually finding feature extracting algorithms does not generalize or scale well to different tasks, which can lead to sub-optimal performance. In this paper, we develop a fully end-to-end model that connects the two phases and optimizes them jointly. In addition, we restructure the current datasets to enable the fully end-to-end training. Furthermore, to reduce the computational overhead brought by the end-to-end model, we introduce a sparse cross-modal attention mechanism for the feature extraction. Experimental results show that our fully end-to-end model significantly surpasses the current state-of-the-art models based on the two-phase pipeline. Moreover, by adding the sparse cross-modal attention, our model can maintain the performance with around half less computation in the feature extraction part of the model.
%R 10.18653/v1/2021.naacl-main.417
%U https://aclanthology.org/2021.naacl-main.417
%U https://doi.org/10.18653/v1/2021.naacl-main.417
%P 5305-5316
Markdown (Informal)
[Multimodal End-to-End Sparse Model for Emotion Recognition](https://aclanthology.org/2021.naacl-main.417) (Dai et al., NAACL 2021)
ACL
- Wenliang Dai, Samuel Cahyawijaya, Zihan Liu, and Pascale Fung. 2021. Multimodal End-to-End Sparse Model for Emotion Recognition. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5305–5316, Online. Association for Computational Linguistics.