An effective emotion tendency perception model in empathic dialogue.

The effectiveness of open-domain dialogue systems depends heavily on emotion. In dialogue systems, previous models primarily detected emotions by looking for emotional words embedded in sentences. However, they did not precisely quantify the association of all words with emotions, which has led to a...

Full description

Bibliographic Details
Main Authors: Jiancu Chen, Siyuan Yang, Jiang Xiong, Yiping Xiong
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2023-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0282926
_version_ 1797843104520208384
author Jiancu Chen
Siyuan Yang
Jiang Xiong
Yiping Xiong
author_facet Jiancu Chen
Siyuan Yang
Jiang Xiong
Yiping Xiong
author_sort Jiancu Chen
collection DOAJ
description The effectiveness of open-domain dialogue systems depends heavily on emotion. In dialogue systems, previous models primarily detected emotions by looking for emotional words embedded in sentences. However, they did not precisely quantify the association of all words with emotions, which has led to a certain bias. To overcome this issue, we propose an emotion tendency perception model. The model uses an emotion encoder to accurately quantify the emotional tendencies of all words. Meanwhile, it uses a shared fusion decoder to equip the decoder with the sentiment and semantic capabilities of the encoder. We conducted extensive evaluations on Empathetic Dialogue. Experimental results demonstrate its efficacy. Compared with the state of the art, our approach has distinctive advantages.
first_indexed 2024-04-09T16:59:21Z
format Article
id doaj.art-55e10bc5295640eeae9a1c630ef3491a
institution Directory Open Access Journal
issn 1932-6203
language English
last_indexed 2024-04-09T16:59:21Z
publishDate 2023-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj.art-55e10bc5295640eeae9a1c630ef3491a2023-04-21T05:33:08ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01183e028292610.1371/journal.pone.0282926An effective emotion tendency perception model in empathic dialogue.Jiancu ChenSiyuan YangJiang XiongYiping XiongThe effectiveness of open-domain dialogue systems depends heavily on emotion. In dialogue systems, previous models primarily detected emotions by looking for emotional words embedded in sentences. However, they did not precisely quantify the association of all words with emotions, which has led to a certain bias. To overcome this issue, we propose an emotion tendency perception model. The model uses an emotion encoder to accurately quantify the emotional tendencies of all words. Meanwhile, it uses a shared fusion decoder to equip the decoder with the sentiment and semantic capabilities of the encoder. We conducted extensive evaluations on Empathetic Dialogue. Experimental results demonstrate its efficacy. Compared with the state of the art, our approach has distinctive advantages.https://doi.org/10.1371/journal.pone.0282926
spellingShingle Jiancu Chen
Siyuan Yang
Jiang Xiong
Yiping Xiong
An effective emotion tendency perception model in empathic dialogue.
PLoS ONE
title An effective emotion tendency perception model in empathic dialogue.
title_full An effective emotion tendency perception model in empathic dialogue.
title_fullStr An effective emotion tendency perception model in empathic dialogue.
title_full_unstemmed An effective emotion tendency perception model in empathic dialogue.
title_short An effective emotion tendency perception model in empathic dialogue.
title_sort effective emotion tendency perception model in empathic dialogue
url https://doi.org/10.1371/journal.pone.0282926
work_keys_str_mv AT jiancuchen aneffectiveemotiontendencyperceptionmodelinempathicdialogue
AT siyuanyang aneffectiveemotiontendencyperceptionmodelinempathicdialogue
AT jiangxiong aneffectiveemotiontendencyperceptionmodelinempathicdialogue
AT yipingxiong aneffectiveemotiontendencyperceptionmodelinempathicdialogue
AT jiancuchen effectiveemotiontendencyperceptionmodelinempathicdialogue
AT siyuanyang effectiveemotiontendencyperceptionmodelinempathicdialogue
AT jiangxiong effectiveemotiontendencyperceptionmodelinempathicdialogue
AT yipingxiong effectiveemotiontendencyperceptionmodelinempathicdialogue