Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations

Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation. In this work, we study the problem of mixed-initiati...

Full description

Saved in:
Bibliographic Details
Main Authors: DENG, Yang, ZHANG, Wenxuan, YUAN, Yifei, LAM, Wai
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9124
https://ink.library.smu.edu.sg/context/sis_research/article/10127/viewcontent/2023.acl_long.225.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10127
record_format dspace
spelling sg-smu-ink.sis_research-101272024-08-01T14:27:43Z Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations DENG, Yang ZHANG, Wenxuan YUAN, Yifei LAM, Wai Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation. In this work, we study the problem of mixed-initiative ESC where the user and system can both take the initiative in leading the conversation. Specifically, we conduct a novel analysis on mixed-initiative ESC systems with a tailor-designed schema that divides utterances into different types with speaker roles and initiative types. Four emotional support metrics are proposed to evaluate the mixed-initiative interactions. The analysis reveals the necessity and challenges of building mixed-initiative ESC systems. In the light of this, we propose a knowledge-enhanced mixed-initiative framework (KEMI) for ESC, which retrieves actual case knowledge from a large-scale mental health knowledge graph for generating mixed-initiative responses. Experimental results on two ESC datasets show the superiority of KEMI in both content-preserving evaluation and mixed initiative related analyses. 2023-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9124 info:doi/10.18653/v1/2023.acl-long.225 https://ink.library.smu.edu.sg/context/sis_research/article/10127/viewcontent/2023.acl_long.225.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
spellingShingle Databases and Information Systems
DENG, Yang
ZHANG, Wenxuan
YUAN, Yifei
LAM, Wai
Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
description Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and addressing their problems during the conversation. In this work, we study the problem of mixed-initiative ESC where the user and system can both take the initiative in leading the conversation. Specifically, we conduct a novel analysis on mixed-initiative ESC systems with a tailor-designed schema that divides utterances into different types with speaker roles and initiative types. Four emotional support metrics are proposed to evaluate the mixed-initiative interactions. The analysis reveals the necessity and challenges of building mixed-initiative ESC systems. In the light of this, we propose a knowledge-enhanced mixed-initiative framework (KEMI) for ESC, which retrieves actual case knowledge from a large-scale mental health knowledge graph for generating mixed-initiative responses. Experimental results on two ESC datasets show the superiority of KEMI in both content-preserving evaluation and mixed initiative related analyses.
format text
author DENG, Yang
ZHANG, Wenxuan
YUAN, Yifei
LAM, Wai
author_facet DENG, Yang
ZHANG, Wenxuan
YUAN, Yifei
LAM, Wai
author_sort DENG, Yang
title Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
title_short Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
title_full Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
title_fullStr Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
title_full_unstemmed Knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
title_sort knowledge-enhanced mixed-initiative dialogue system for emotional support conversations
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/9124
https://ink.library.smu.edu.sg/context/sis_research/article/10127/viewcontent/2023.acl_long.225.pdf
_version_ 1814047748902617088