Proposta de Arquitetura de Software para um Chatbot com aprendizagem
Abstract
A weakness of the most commonly used chatbot agents today is that they are not designed to learn during the conversation process. Their knowledge is fixed during the project and they do not take advantage of the interaction with users to evolve their knowledge and their ability to dialogue. In this work, the design of a Chatbot with lifelong learning is inserted in the Reinforcement Learning framework. Although reinforcement learning has been used before, the literature review presented shows that this proposal is innovative.
Keywords:
Conversational agent, Continuous learning, Dialogue man-machine, Chatbot, Virtual assistant
References
Adamopoulou, E. and Moussiades, L. (2020). An overview of chatbot technology. In IFIP International Conference on Artificial Intelligence Applications and Innovations, pages 373–383. Springer.
Io, H. and Lee, C. (2017). Chatbots and conversational agents: A bibliometric analysis. In 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), pages 215–219. IEEE.
Li, J., Monroe, W., Ritter, A., Galley, M., Gão, J., and Jurafsky, D. (2016). Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541.
Liu, J., Pan, F., and Luo, L. (2020). Gochat: Goal-oriented chatbots with hierarchical reinforcement learning. arXiv preprint arXiv:2005.11729.
Nishimoto, B. and Costa, A. H. R. (2019). Dialogue management with deep reinforcement learning: Balancing exploration and exploitation. In 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pages 449–454. IEEE.
Norvig, P. and Russell, S. (2014). Inteligência artificial: Tradução da 3a Edição. Elsevier Brasil.
Nuruzzaman, M. and Hussain, O. K. (2018). A survey on chatbot implementation in customer service industry through deep neural networks. In 2018 IEEE 15th International Conference on e-Business Engineering (ICEBE), pages 54–61. IEEE.
Ricciardelli, E. and Biswas, D. (2019). Self-improving chatbots based on reinforcement learning. In 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making.
Serban, I. V., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian, S., Kim, T., Pieper, M., Chandar, S., Ke, N. R., et al. (2017). A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349.
Sutton, R. S. and Barto, A. G. (1998). Reinforcement learning i: Introduction.
Yin, C., Zhang, R., Qi, J., Sun, Y., and Tan, T. (2018). Context-uncertainty-aware chatbot action selection via parameterized auxiliary reinforcement learning. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 500–512. Springer.
Io, H. and Lee, C. (2017). Chatbots and conversational agents: A bibliometric analysis. In 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), pages 215–219. IEEE.
Li, J., Monroe, W., Ritter, A., Galley, M., Gão, J., and Jurafsky, D. (2016). Deep reinforcement learning for dialogue generation. arXiv preprint arXiv:1606.01541.
Liu, J., Pan, F., and Luo, L. (2020). Gochat: Goal-oriented chatbots with hierarchical reinforcement learning. arXiv preprint arXiv:2005.11729.
Nishimoto, B. and Costa, A. H. R. (2019). Dialogue management with deep reinforcement learning: Balancing exploration and exploitation. In 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pages 449–454. IEEE.
Norvig, P. and Russell, S. (2014). Inteligência artificial: Tradução da 3a Edição. Elsevier Brasil.
Nuruzzaman, M. and Hussain, O. K. (2018). A survey on chatbot implementation in customer service industry through deep neural networks. In 2018 IEEE 15th International Conference on e-Business Engineering (ICEBE), pages 54–61. IEEE.
Ricciardelli, E. and Biswas, D. (2019). Self-improving chatbots based on reinforcement learning. In 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making.
Serban, I. V., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian, S., Kim, T., Pieper, M., Chandar, S., Ke, N. R., et al. (2017). A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349.
Sutton, R. S. and Barto, A. G. (1998). Reinforcement learning i: Introduction.
Yin, C., Zhang, R., Qi, J., Sun, Y., and Tan, T. (2018). Context-uncertainty-aware chatbot action selection via parameterized auxiliary reinforcement learning. In Pacific-Asia Conference on Knowledge Discovery and Data Mining, pages 500–512. Springer.
Published
2020-09-10
How to Cite
SOARES, Jéferson; MAIA, José.
Proposta de Arquitetura de Software para um Chatbot com aprendizagem. In: REGIONAL SCHOOL ON COMPUTING OF CEARÁ, MARANHÃO, AND PIAUÍ (ERCEMAPI), 8. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 197-203.
DOI: https://doi.org/10.5753/ercemapi.2020.11485.
