@inproceedings{xu-etal-2024-escp-enhancing,
title = "{ESCP}: Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes",
author = "Xu, Xiujuan and
Shi, Xiaoxiao and
Zhao, Zhehuan and
Liu, Yu",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.555",
pages = "6278--6287",
abstract = "Emotion Recognition in Conversation (ERC) aims to analyze the speaker{'}s emotional state in a conversation. Fully mining the information in multimodal and historical utterances plays a crucial role in the performance of the model. However, recent works in ERC focus on historical utterances modeling and generally concatenate the multimodal features directly, which neglects mining deep multimodal information and brings redundancy at the same time. To address the shortcomings of existing models, we propose a novel model, termed Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes (ESCP). ESCP employs a directed acyclic graph (DAG) to model historical utterances in a conversation and incorporates a contextual prefix containing the sentiment and semantics of historical utterances. By adding speech and contextual prefixes, the inter- and intra-modal emotion information is efficiently modeled using the prior knowledge of the large-scale pre-trained model. Experiments conducted on several public benchmarks demonstrate that the proposed approach achieves state-of-the-art (SOTA) performances. These results affirm the effectiveness of the novel ESCP model and underscore the significance of incorporating speech and contextual prefixes to guide the pre-trained model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-escp-enhancing">
<titleInfo>
<title>ESCP: Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiujuan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoxiao</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhehuan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion Recognition in Conversation (ERC) aims to analyze the speaker’s emotional state in a conversation. Fully mining the information in multimodal and historical utterances plays a crucial role in the performance of the model. However, recent works in ERC focus on historical utterances modeling and generally concatenate the multimodal features directly, which neglects mining deep multimodal information and brings redundancy at the same time. To address the shortcomings of existing models, we propose a novel model, termed Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes (ESCP). ESCP employs a directed acyclic graph (DAG) to model historical utterances in a conversation and incorporates a contextual prefix containing the sentiment and semantics of historical utterances. By adding speech and contextual prefixes, the inter- and intra-modal emotion information is efficiently modeled using the prior knowledge of the large-scale pre-trained model. Experiments conducted on several public benchmarks demonstrate that the proposed approach achieves state-of-the-art (SOTA) performances. These results affirm the effectiveness of the novel ESCP model and underscore the significance of incorporating speech and contextual prefixes to guide the pre-trained model.</abstract>
<identifier type="citekey">xu-etal-2024-escp-enhancing</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.555</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6278</start>
<end>6287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ESCP: Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes
%A Xu, Xiujuan
%A Shi, Xiaoxiao
%A Zhao, Zhehuan
%A Liu, Yu
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F xu-etal-2024-escp-enhancing
%X Emotion Recognition in Conversation (ERC) aims to analyze the speaker’s emotional state in a conversation. Fully mining the information in multimodal and historical utterances plays a crucial role in the performance of the model. However, recent works in ERC focus on historical utterances modeling and generally concatenate the multimodal features directly, which neglects mining deep multimodal information and brings redundancy at the same time. To address the shortcomings of existing models, we propose a novel model, termed Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes (ESCP). ESCP employs a directed acyclic graph (DAG) to model historical utterances in a conversation and incorporates a contextual prefix containing the sentiment and semantics of historical utterances. By adding speech and contextual prefixes, the inter- and intra-modal emotion information is efficiently modeled using the prior knowledge of the large-scale pre-trained model. Experiments conducted on several public benchmarks demonstrate that the proposed approach achieves state-of-the-art (SOTA) performances. These results affirm the effectiveness of the novel ESCP model and underscore the significance of incorporating speech and contextual prefixes to guide the pre-trained model.
%U https://aclanthology.org/2024.lrec-main.555
%P 6278-6287
Markdown (Informal)
[ESCP: Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes](https://aclanthology.org/2024.lrec-main.555) (Xu et al., LREC-COLING 2024)
ACL