TY - GEN
T1 - Improving Personality Consistency in Conversation by Persona Extending
AU - Liu, Yifan
AU - Wei, Wei
AU - Liu, Jiayi
AU - Mao, Xianling
AU - Fang, Rui
AU - Chen, Dangyang
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/10/17
Y1 - 2022/10/17
N2 - Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate responses in light of static predefined personas depicted with textual description, which may severely restrict the interactivity of human and the chatbot, especially when the agent needs to answer the query excluded in the predefined personas, which is so-called out-of-predefined persona problem (named OOP for simplicity). To alleviate the problem, in this paper we propose a novel retrieval-to-prediction paradigm consisting of two subcomponents, namely, (1) Persona Retrieval Model (PRM), it retrieves a persona from a global collection based on a Natural Language Inference (NLI) model, the inferred persona is consistent with the predefined personas; and (2) Posterior-scored Transformer (PS-Transformer), it adopts a persona posterior distribution that further considers the actual personas used in the ground response, maximally mitigating the gap between training and inferring. Furthermore, we present a dataset called IT-ConvAI2 that first highlights the OOP problem in personalized dialogue. Extensive experiments on both IT-ConvAI2 and ConvAI2 demonstrate that our proposed model yields considerable improvements in both automatic metrics and human evaluations.
AB - Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate responses in light of static predefined personas depicted with textual description, which may severely restrict the interactivity of human and the chatbot, especially when the agent needs to answer the query excluded in the predefined personas, which is so-called out-of-predefined persona problem (named OOP for simplicity). To alleviate the problem, in this paper we propose a novel retrieval-to-prediction paradigm consisting of two subcomponents, namely, (1) Persona Retrieval Model (PRM), it retrieves a persona from a global collection based on a Natural Language Inference (NLI) model, the inferred persona is consistent with the predefined personas; and (2) Posterior-scored Transformer (PS-Transformer), it adopts a persona posterior distribution that further considers the actual personas used in the ground response, maximally mitigating the gap between training and inferring. Furthermore, we present a dataset called IT-ConvAI2 that first highlights the OOP problem in personalized dialogue. Extensive experiments on both IT-ConvAI2 and ConvAI2 demonstrate that our proposed model yields considerable improvements in both automatic metrics and human evaluations.
KW - dialogue generation
KW - persona expanding
KW - personality consistency
UR - http://www.scopus.com/inward/record.url?scp=85140825030&partnerID=8YFLogxK
U2 - 10.1145/3511808.3557359
DO - 10.1145/3511808.3557359
M3 - Conference contribution
AN - SCOPUS:85140825030
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 1350
EP - 1359
BT - CIKM 2022 - Proceedings of the 31st ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 31st ACM International Conference on Information and Knowledge Management, CIKM 2022
Y2 - 17 October 2022 through 21 October 2022
ER -