Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation

Enabling machines to emotion recognition in conversation is challenging, mainly because the information in human dialogue innately conveys emotions by long-term experience, abundant knowledge, context, and the intricate patterns between the affective states. We address the task of emotion recognitio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Fuji Ren, Tianhao She
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Affective computing text emotion classification emotion recognition in conversation Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/62ba2b70671c49179cb2c32719c6cbd2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:62ba2b70671c49179cb2c32719c6cbd2
record_format	dspace
spelling	oai:doaj.org-article:62ba2b70671c49179cb2c32719c6cbd22021-11-25T00:00:37ZUtilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation2169-353610.1109/ACCESS.2021.3128277https://doaj.org/article/62ba2b70671c49179cb2c32719c6cbd22021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9615035/https://doaj.org/toc/2169-3536Enabling machines to emotion recognition in conversation is challenging, mainly because the information in human dialogue innately conveys emotions by long-term experience, abundant knowledge, context, and the intricate patterns between the affective states. We address the task of emotion recognition in conversations using external knowledge to enhance semantics. We propose KES model, a new framework that incorporates different elements of external knowledge and conversational semantic role labeling, where build upon them to learn interactions between interlocutors participating in a conversation. We design a self-attention layer specialized for enhanced semantic text features with external commonsense knowledge. Then, two different networks composed of LSTM are responsible for tracking individual internal state and context external state. In addition, the proposed model has experimented on three datasets in emotion detection in conversation. The experimental results show that our model outperforms the state-of-the-art approaches on most of the tested datasets.Fuji RenTianhao SheIEEEarticleAffective computingtext emotion classificationemotion recognition in conversationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 154947-154956 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Affective computing text emotion classification emotion recognition in conversation Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Affective computing text emotion classification emotion recognition in conversation Electrical engineering. Electronics. Nuclear engineering TK1-9971 Fuji Ren Tianhao She Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
description	Enabling machines to emotion recognition in conversation is challenging, mainly because the information in human dialogue innately conveys emotions by long-term experience, abundant knowledge, context, and the intricate patterns between the affective states. We address the task of emotion recognition in conversations using external knowledge to enhance semantics. We propose KES model, a new framework that incorporates different elements of external knowledge and conversational semantic role labeling, where build upon them to learn interactions between interlocutors participating in a conversation. We design a self-attention layer specialized for enhanced semantic text features with external commonsense knowledge. Then, two different networks composed of LSTM are responsible for tracking individual internal state and context external state. In addition, the proposed model has experimented on three datasets in emotion detection in conversation. The experimental results show that our model outperforms the state-of-the-art approaches on most of the tested datasets.
format	article
author	Fuji Ren Tianhao She
author_facet	Fuji Ren Tianhao She
author_sort	Fuji Ren
title	Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
title_short	Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
title_full	Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
title_fullStr	Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
title_full_unstemmed	Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
title_sort	utilizing external knowledge to enhance semantics in emotion detection in conversation
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/62ba2b70671c49179cb2c32719c6cbd2
work_keys_str_mv	AT fujiren utilizingexternalknowledgetoenhancesemanticsinemotiondetectioninconversation AT tianhaoshe utilizingexternalknowledgetoenhancesemanticsinemotiondetectioninconversation
_version_	1718414696854323200

Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation

Ejemplares similares