Yuta Watanabe
ABSTRACT
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.
- Chris L Baker, Julian Jara-Ettinger, Rebecca Saxe, and Joshua B Tenenbaum. 2017. Rational quantitative attribution of beliefs, desires and percepts in human mentalizing. Nature Human Behaviour 1, 4 (2017), 1–10.Google Scholar
Cross Ref
- Qibin Chen, Junyang Lin, Yichang Zhang, Ming Ding, Yukuo Cen, Hongxia Yang, and Jie Tang. 2019. Towards Knowledge-Based Recommender Dialog System. arxiv:1908.05391 [cs.CL]Google Scholar
- Hamidreza. Chinaei. 2016. Building Dialogue POMDPs from Expert Dialogues An end-to-end approach (1st ed. 2016. ed.). Springer International Publishing, Cham.Google Scholar
- Yosuke Fukuchi, Masahiko Osawa, Hiroshi Yamakawa, Tatsuji Takahashi, and Michita Imai. 2018. Bayesian Inference of Self-Intention Attributed by Observer. In Proceedings of the 6th International Conference on Human-Agent Interaction (Southampton, United Kingdom) (HAI ’18). Association for Computing Machinery, New York, NY, USA, 3–10. https://doi.org/10.1145/3284432.3284438Google ScholarDigital Library
- Chiori Hori, Julien Perez, Ryuichiro Higashinaka, Takaaki Hori, Y-Lan Boureau, Michimasa Inaba, Yuiko Tsunomori, Tetsuro Takahashi, Koichiro Yoshino, and Seokhwan Kim. 2019. Overview of the sixth dialog system technology challenge: DSTC6. Computer Speech & Language 55 (2019), 1–25.Google ScholarCross Ref
- Chaitanya K. Joshi, Fei Mi, and Boi Faltings. 2017. Personalization in Goal-Oriented Dialog. arxiv:1706.07503 [cs.CL]Google Scholar
- Timo. Koski. 2009. Bayesian networks an introduction. John Wiley and Sons, Hoboken, NJ. 12 pages.Google Scholar
- William A. Link. 2010. Bayesian inference with ecological applications (1st ed. ed.). Academic Press, Amsterdam.Google Scholar
- David Premack and Guy Woodruff. 1978. Does the chimpanzee have a theory of mind?Behavioral and brain sciences 1, 4 (1978), 515–526.Google Scholar
- Kun Qian and Zhou Yu. 2019. Domain adaptive dialog generation via meta learning. arXiv preprint arXiv:1906.03520(2019).Google Scholar
- Roshni R. Ramnani, Shubhashis Sengupta, and Poulami Debnath. 2018. Intelligent Travel Advisor: A Goal Oriented Virtual Agent with Task Modeling, Planning and User Personalization. In Proceedings of the 18th International Conference on Intelligent Virtual Agents (Sydney, NSW, Australia) (IVA ’18). Association for Computing Machinery, New York, NY, USA, 341–342. https://doi.org/10.1145/3267851.3267885Google ScholarDigital Library
- Weiyan Shi and Zhou Yu. 2018. Sentiment adaptive end-to-end dialog systems. arXiv preprint arXiv:1804.10731(2018).Google Scholar
- Yusuke Takimoto, Yosuke Fukuchi, Shoya Matsumori, and Michita Imai. 2020. SLAM-Inspired Simultaneous Contextualization and Interpreting for Incremental Conversation Sentences. arxiv:2005.14662 [cs.CL]Google Scholar
- Xiang Zhang and Qiang Yang. 2019. Transfer hierarchical attention network for generative dialog system. International Journal of Automation and Computing 16, 6 (2019), 720–736.Google ScholarDigital Library
Index Terms
- Inferring Human Beliefs and Desires from their Actions and the Content of their Utterances
Recommendations
Bayesian Inference of Self-intention Attributed by Observer
HAI '18: Proceedings of the 6th International Conference on Human-Agent InteractionMost of agents that learn policy for tasks with reinforcement learning (RL) lack the ability to communicate with people, which makes human-agent collaboration challenging. We believe that, in order for RL agents to comprehend utterances from human ...
Mean-field variational approximate Bayesian inference for latent variable models
The ill-posed nature of missing variable models offers a challenging testing ground for new computational techniques. This is the case for the mean-field variational Bayesian inference. The behavior of this approach in the setting of the Bayesian probit ...
Comments