Abstract
A virtual conversational agent is designed based on a cognitive model integrated with neural network model named BERT and large language model ChatGPT. The system was tested in a Turing-test-like experiment with human participants, using a limited paradigm of registration of a guest in a hotel. Performance of the agent on several scales matches human performance, while in empathy it showed a significantly higher score compared to humans. The narrowly designed prototype proves the concept and suggest future applications to general open-ended paradigms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Russel, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 4th Global Pearson Education Limited, London (2013)
Oishi, E.: Austin’s speech act theory and the speech situation. Eser. Filos. 1, 1–14 (2006)
Acheampong, F.A., Nunoo-Mensah, H., Chen, W.: Transformer models for text-based emotion detection: a review of BERT-based approaches. Artif. Intell. Rev. 2021, 1–41 (2021)
Garrido-Merchán, E.C., et al.: Comparing BERT against traditional machine learning models in text classification. J. Comput. Cogn. Eng. (2022). https://doi.org/10.47852/bonviewJCCE3202838
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Long Beach, CA (2017)
Zhang, H., Song, H., Li, S., Zhou, M., Song, D.: Survey of controllable text generation using transformer-based pre-trained language models. ACM Comput. Surv. J. 37(4), Article 111 (2023)
Dathathri, S., et al.: Plug and play language models: a simple approach to controlled text generation. arXiv:1912.02164 (2019)
Samsonovich, A.V.: Socially emotional brain-inspired cognitive architecture framework for artificial intelligence. Cogn. Syst. Res. 60, 57–76 (2020)
Li, J., et al.: Pretrained language models for text generation: a survey. arXiv:2105.10311 (2021)
Fitrianie, S., et al.: The 19 unifying questionnaire constructs of artificial social agents: an IVA community analysis. In: Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents, pp. 1–8 (2020)
Samsonovich, A.V., Ascoli, G.A.: The conscious self: ontology, epistemology and the mirror quest. Cortex 41(5), 621–636 (2005). https://doi.org/10.1016/S0010-9452(08)70280-6
Samsonovich, A.V., De Jong, K.A., Kitsantas, A., Peters, E.E., Dabbagh, N., Kalbfleisch, M.L.: Cognitive constructor: an intelligent tutoring system based on a biologically inspired cognitive architecture (BICA). Front. Artif. Intell. Appl. 171(1), 311–325 (2008). ISSN: 09226389
Samsonovich, A.V., Ascoli, G.A.: Cognitive map dimensions of the human value system extracted from natural language. Front. Artif. Intell. Appl. 157, 111–124 (2007). ISSN: 09226389
Samsonovich, A.V., Ascoli, G.A.: Augmenting weak semantic cognitive maps with an “abstractness” dimension. Comput. Intell. Neurosci. 2013, Article number 308176 (2013). https://doi.org/10.1155/2013/308176
Acknowledgments
This work was supported by the Russian Science Foundation Grant #22-11-00213, https://rscf.ru/en/project/22-11-00213/.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Khabarov, D., Samsonovich, A.V. (2024). Registrar: A Social Conversational Agent Based on Cognitive and Statistical Models for a Limited Paradigm. In: Samsonovich, A.V., Liu, T. (eds) Biologically Inspired Cognitive Architectures 2023. BICA 2023. Studies in Computational Intelligence, vol 1130. Springer, Cham. https://doi.org/10.1007/978-3-031-50381-8_46
Download citation
DOI: https://doi.org/10.1007/978-3-031-50381-8_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50380-1
Online ISBN: 978-3-031-50381-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)