TY - GEN
T1 - Plug and Play Conversations
T2 - 26th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2023
AU - Sun, Xin
AU - Krahmer, Emiel
AU - de Wit, Jan
AU - Wiers, Reinout
AU - Bosch, Jos A.
N1 - Publisher Copyright: © 2023 Owner/Author.
PY - 2023/10/14
Y1 - 2023/10/14
N2 - Conversational agents (CAs) for psychotherapy pose unique challenges (e.g., reliance on domain experts to pre-script large amounts of therapeutical dialogues). To tackle these challenges, we propose a modular approach to develop such CA, called Micro-Conversation Scheme (MCS). Conversations can be algorithmically extended in MCS by combining different micro-conversations (MC), which isolate single therapeutical topic. The sequencing of MC is managed by a Connector component, connecting MC into longer conversations with context. Additionally, MCS integrates natural language generation (NLG) models as plugins for generating counseling-style utterances (e.g., reflections). Moreover, MCS adopts interactive learning to continuously improve CA based on human feedback. MCS provides a solution to the challenges of complex-to-design and difficult-to-extend conversations, and inability of CA to flexibly generate context-appropriate counseling-style utterances for psychotherapy. MCS is expected to benefit the community by promoting the collaboration between conversational designers and developers while preserve their independence during the development of CAs.
AB - Conversational agents (CAs) for psychotherapy pose unique challenges (e.g., reliance on domain experts to pre-script large amounts of therapeutical dialogues). To tackle these challenges, we propose a modular approach to develop such CA, called Micro-Conversation Scheme (MCS). Conversations can be algorithmically extended in MCS by combining different micro-conversations (MC), which isolate single therapeutical topic. The sequencing of MC is managed by a Connector component, connecting MC into longer conversations with context. Additionally, MCS integrates natural language generation (NLG) models as plugins for generating counseling-style utterances (e.g., reflections). Moreover, MCS adopts interactive learning to continuously improve CA based on human feedback. MCS provides a solution to the challenges of complex-to-design and difficult-to-extend conversations, and inability of CA to flexibly generate context-appropriate counseling-style utterances for psychotherapy. MCS is expected to benefit the community by promoting the collaboration between conversational designers and developers while preserve their independence during the development of CAs.
KW - Collaborative development
KW - hybrid conversational agent
KW - modular and interactive development
UR - http://www.scopus.com/inward/record.url?scp=85176256459&partnerID=8YFLogxK
U2 - https://doi.org/10.1145/3584931.3606998
DO - https://doi.org/10.1145/3584931.3606998
M3 - Conference contribution
T3 - Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW
SP - 50
EP - 55
BT - CSCW 2023 Companion - Conference Companion Publication of the 2023 Computer Supported Cooperative Work and Social Computing
A2 - Ames, Morgan
A2 - Fussell, Susan
A2 - Gilbert, Eric
A2 - Liao, Vera
A2 - Ma, Xiaojuan
A2 - Page, Xinru
A2 - Rouncefield, Mark
A2 - Singh, Vivek
A2 - Wisniewski, Pamela
A2 - Ames, M.
A2 - Fussell, S.
A2 - Gilbert, E.
A2 - Liao, V.
A2 - Ma, X.
A2 - Page, X.
A2 - Rouncefield, M.
A2 - Singh, V.
A2 - Wisniewski, P.
PB - Association for Computing Machinery
CY - New York, NY
Y2 - 14 October 2023 through 18 October 2023
ER -