TY - GEN
T1 - Inferring human beliefs and desires from their actions and the content of their utterances
AU - Watanabe, Yuta
AU - Fukuchi, Yosuke
AU - Maekawa, Tomoyuki
AU - Matsumori, Shoya
AU - Imai, Michita
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number JP21J1 3789 and JST CREST Grant Number JPMJCR19A1, Japan
Publisher Copyright:
© 2021 Owner/Author.
PY - 2021/11/9
Y1 - 2021/11/9
N2 - To create dialogue systems that provide information a user needs to know at an opportune moment, it is important to infer the user's mental states such as his/her beliefs and desires. There are two types of study on inferring beliefs and desires: one type infers them from actions and the other infers them from the content of utterances. However, a method to infer beliefs and desires from both kinds of inference in an integrated way has not yet been established. In this paper, we propose Multimodal Inference of Mind Simultaneous Contextualization and Interpreting (MIoM SCAIN), a system for sequentially inferring users' beliefs and desires on the basis of their walking behaviors and the content of their utterances. In our evaluation, we compared inferences of MIoM SCAIN with those of baselines that use either walking behaviors or the content of utterances. MIoM SCAIN's predictions showed more correlation with subjective judgements compared with the baselines, indicating that the inference of beliefs and desires from both walking behaviors and utterance content is possible.
AB - To create dialogue systems that provide information a user needs to know at an opportune moment, it is important to infer the user's mental states such as his/her beliefs and desires. There are two types of study on inferring beliefs and desires: one type infers them from actions and the other infers them from the content of utterances. However, a method to infer beliefs and desires from both kinds of inference in an integrated way has not yet been established. In this paper, we propose Multimodal Inference of Mind Simultaneous Contextualization and Interpreting (MIoM SCAIN), a system for sequentially inferring users' beliefs and desires on the basis of their walking behaviors and the content of their utterances. In our evaluation, we compared inferences of MIoM SCAIN with those of baselines that use either walking behaviors or the content of utterances. MIoM SCAIN's predictions showed more correlation with subjective judgements compared with the baselines, indicating that the inference of beliefs and desires from both walking behaviors and utterance content is possible.
KW - Bayesian inference
KW - Dialogue system
KW - Human computer interaction
KW - Partially observable markov decision processes
KW - Theory of mind
UR - http://www.scopus.com/inward/record.url?scp=85119333596&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119333596&partnerID=8YFLogxK
U2 - 10.1145/3472307.3484668
DO - 10.1145/3472307.3484668
M3 - Conference contribution
AN - SCOPUS:85119333596
T3 - HAI 2021 - Proceedings of the 9th International User Modeling, Adaptation and Personalization Human-Agent Interaction
SP - 391
EP - 395
BT - HAI 2021 - Proceedings of the 9th International User Modeling, Adaptation and Personalization Human-Agent Interaction
PB - Association for Computing Machinery, Inc
T2 - 9th International User Modeling, Adaptation and Personalization Human-Agent Interaction, HAI 2021
Y2 - 9 November 2021 through 11 November 2021
ER -