@inproceedings{zhang-li-2023-cross,
title = "A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Recognition in Conversation",
author = "Zhang, Xiaoheng and
Li, Yang",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.732/",
doi = "10.18653/v1/2023.acl-long.732",
pages = "13099--13110",
abstract = "Emotion recognition in conversation (ERC) has attracted enormous attention for its applications in empathetic dialogue systems. However, most previous researches simply concatenate multimodal representations, leading to an accumulation of redundant information and a limited context interaction between modalities. Furthermore, they only consider simple contextual features ignoring semantic clues, resulting in an insufficient capture of the semantic coherence and consistency in conversations. To address these limitations, we propose a cross-modality context fusion and semantic refinement network (CMCF-SRNet). Specifically, we first design a cross-modal locality-constrained transformer to explore the multimodal interaction. Second, we investigate a graph-based semantic refinement transformer, which solves the limitation of insufficient semantic relationship information between utterances. Extensive experiments on two public benchmark datasets show the effectiveness of our proposed method compared with other state-of-the-art methods, indicating its potential application in emotion recognition. Our model will be available at \url{https://github.com/zxiaohen/CMCF-SRNet}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-li-2023-cross">
<titleInfo>
<title>A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion recognition in conversation (ERC) has attracted enormous attention for its applications in empathetic dialogue systems. However, most previous researches simply concatenate multimodal representations, leading to an accumulation of redundant information and a limited context interaction between modalities. Furthermore, they only consider simple contextual features ignoring semantic clues, resulting in an insufficient capture of the semantic coherence and consistency in conversations. To address these limitations, we propose a cross-modality context fusion and semantic refinement network (CMCF-SRNet). Specifically, we first design a cross-modal locality-constrained transformer to explore the multimodal interaction. Second, we investigate a graph-based semantic refinement transformer, which solves the limitation of insufficient semantic relationship information between utterances. Extensive experiments on two public benchmark datasets show the effectiveness of our proposed method compared with other state-of-the-art methods, indicating its potential application in emotion recognition. Our model will be available at https://github.com/zxiaohen/CMCF-SRNet.</abstract>
<identifier type="citekey">zhang-li-2023-cross</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.732</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.732/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13099</start>
<end>13110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Recognition in Conversation
%A Zhang, Xiaoheng
%A Li, Yang
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F zhang-li-2023-cross
%X Emotion recognition in conversation (ERC) has attracted enormous attention for its applications in empathetic dialogue systems. However, most previous researches simply concatenate multimodal representations, leading to an accumulation of redundant information and a limited context interaction between modalities. Furthermore, they only consider simple contextual features ignoring semantic clues, resulting in an insufficient capture of the semantic coherence and consistency in conversations. To address these limitations, we propose a cross-modality context fusion and semantic refinement network (CMCF-SRNet). Specifically, we first design a cross-modal locality-constrained transformer to explore the multimodal interaction. Second, we investigate a graph-based semantic refinement transformer, which solves the limitation of insufficient semantic relationship information between utterances. Extensive experiments on two public benchmark datasets show the effectiveness of our proposed method compared with other state-of-the-art methods, indicating its potential application in emotion recognition. Our model will be available at https://github.com/zxiaohen/CMCF-SRNet.
%R 10.18653/v1/2023.acl-long.732
%U https://aclanthology.org/2023.acl-long.732/
%U https://doi.org/10.18653/v1/2023.acl-long.732
%P 13099-13110
Markdown (Informal)
[A Cross-Modality Context Fusion and Semantic Refinement Network for Emotion Recognition in Conversation](https://aclanthology.org/2023.acl-long.732/) (Zhang & Li, ACL 2023)
ACL