@inproceedings{yun-etal-2024-telme,
title = "{T}el{ME}: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation",
author = "Yun, Taeyang and
Lim, Hyunkuk and
Lee, Jeonghwan and
Song, Min",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.5",
doi = "10.18653/v1/2024.naacl-long.5",
pages = "82--95",
abstract = "Emotion Recognition in Conversation (ERC) plays a crucial role in enabling dialogue sys- tems to effectively respond to user requests. The emotions in a conversation can be identi- fied by the representations from various modal- ities, such as audio, visual, and text. How- ever, due to the weak contribution of non-verbal modalities to recognize emotions, multimodal ERC has always been considered a challenging task. In this paper, we propose Teacher-leading Multimodal fusion network for ERC (TelME). TelME incorporates cross-modal knowledge distillation to transfer information from a lan- guage model acting as the teacher to the non- verbal students, thereby optimizing the efficacy of the weak modalities. We then combine multi- modal features using a shifting fusion approach in which student networks support the teacher. TelME achieves state-of-the-art performance in MELD, a multi-speaker conversation dataset for ERC. Finally, we demonstrate the effec- tiveness of our components through additional experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yun-etal-2024-telme">
<titleInfo>
<title>TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taeyang</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunkuk</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeonghwan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion Recognition in Conversation (ERC) plays a crucial role in enabling dialogue sys- tems to effectively respond to user requests. The emotions in a conversation can be identi- fied by the representations from various modal- ities, such as audio, visual, and text. How- ever, due to the weak contribution of non-verbal modalities to recognize emotions, multimodal ERC has always been considered a challenging task. In this paper, we propose Teacher-leading Multimodal fusion network for ERC (TelME). TelME incorporates cross-modal knowledge distillation to transfer information from a lan- guage model acting as the teacher to the non- verbal students, thereby optimizing the efficacy of the weak modalities. We then combine multi- modal features using a shifting fusion approach in which student networks support the teacher. TelME achieves state-of-the-art performance in MELD, a multi-speaker conversation dataset for ERC. Finally, we demonstrate the effec- tiveness of our components through additional experiments.</abstract>
<identifier type="citekey">yun-etal-2024-telme</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.5</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.5</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>82</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation
%A Yun, Taeyang
%A Lim, Hyunkuk
%A Lee, Jeonghwan
%A Song, Min
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F yun-etal-2024-telme
%X Emotion Recognition in Conversation (ERC) plays a crucial role in enabling dialogue sys- tems to effectively respond to user requests. The emotions in a conversation can be identi- fied by the representations from various modal- ities, such as audio, visual, and text. How- ever, due to the weak contribution of non-verbal modalities to recognize emotions, multimodal ERC has always been considered a challenging task. In this paper, we propose Teacher-leading Multimodal fusion network for ERC (TelME). TelME incorporates cross-modal knowledge distillation to transfer information from a lan- guage model acting as the teacher to the non- verbal students, thereby optimizing the efficacy of the weak modalities. We then combine multi- modal features using a shifting fusion approach in which student networks support the teacher. TelME achieves state-of-the-art performance in MELD, a multi-speaker conversation dataset for ERC. Finally, we demonstrate the effec- tiveness of our components through additional experiments.
%R 10.18653/v1/2024.naacl-long.5
%U https://aclanthology.org/2024.naacl-long.5
%U https://doi.org/10.18653/v1/2024.naacl-long.5
%P 82-95
Markdown (Informal)
[TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation](https://aclanthology.org/2024.naacl-long.5) (Yun et al., NAACL 2024)
ACL