TY - GEN
T1 - Modeling a Conversational Agent using BDI Framework
AU - Ichida, Alexandre Yukio
AU - Meneguzzi, Felipe
PY - 2023/6/7
Y1 - 2023/6/7
N2 - Building conversational agents to help humans in domain-specific tasks is challenging since the agent needs to understand the natural language and act over it while accessing domain expert knowledge. Modern natural language processing techniques led to an expansion of conversational agents, with recent pretrained language models achieving increasingly accurate language recognition results using ever-larger open datasets. However, the black-box nature of such pretrained language models obscures the agent's reasoning and its motivations when responding, leading to unexplained dialogues. We develop a belief-desire-intention (BDI) agent as a task-oriented dialogue system to introduce mental attitudes similar to humans describing their behavior during a dialogue. We compare the resulting model with a pipeline dialogue model by leveraging existing components from dialogue systems and developing the agent's intention selection as a dialogue policy. We show that combining traditional agent modelling approaches, such as BDI, with more recent learning techniques can result in efficient and scrutable dialogue systems.
AB - Building conversational agents to help humans in domain-specific tasks is challenging since the agent needs to understand the natural language and act over it while accessing domain expert knowledge. Modern natural language processing techniques led to an expansion of conversational agents, with recent pretrained language models achieving increasingly accurate language recognition results using ever-larger open datasets. However, the black-box nature of such pretrained language models obscures the agent's reasoning and its motivations when responding, leading to unexplained dialogues. We develop a belief-desire-intention (BDI) agent as a task-oriented dialogue system to introduce mental attitudes similar to humans describing their behavior during a dialogue. We compare the resulting model with a pipeline dialogue model by leveraging existing components from dialogue systems and developing the agent's intention selection as a dialogue policy. We show that combining traditional agent modelling approaches, such as BDI, with more recent learning techniques can result in efficient and scrutable dialogue systems.
KW - autonomous agent
KW - belief-desire-intention
KW - machine learning
KW - task-oriented dialogue systems
UR - http://www.scopus.com/inward/record.url?scp=85162873102&partnerID=8YFLogxK
U2 - 10.1145/3555776.3577657
DO - 10.1145/3555776.3577657
M3 - Published conference contribution
AN - SCOPUS:85162873102
T3 - Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing
SP - 856
EP - 863
BT - Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing
PB - Association for Computing Machinery
T2 - 38th Annual ACM Symposium on Applied Computing, SAC 2023
Y2 - 27 March 2023 through 31 March 2023
ER -