Obtaining Plan Traces from Natural Language Conversations in a Healthcare Chatbot

• Bianca Precebes da Silva UFC
• Maria Viviane de Menezes UFC
• Lívia Almada Cruz UFC
• Bruno da Silva Pinho UFC
• Luis Fernando Oliveira Sousa UFC

DOI: https://doi.org/10.5753/eniac.2025.14239

Resumo

Automated Planning is a subarea of Artificial Intelligence (AI) that studies the deliberative process of choosing actions for an agent to achieve its goals. A planner is a problem-solving algorithm that takes as input a high-level description of the agent and its environment (planning domain) and produces a sequence of actions (plan) that moves the agent from an initial state to a goal state. Acquiring a planning domain can be performed using algorithms that learn the domain description from a kind of specific data (plan traces). Obtaining such plan traces is difficult and a viable strategy is to extract it from Natural Language information. This work aims to build a database of plan traces from Natural Language dialogue data. These data represent conversations between real users and a healthcare chatbot.

Referências

(2024). Knowledge engineering for planning and scheduling (keps) workshop – icaps 2024. [link]. Accessed: 2025-05-09.

AI, E. (2024). spacy: Industrial-strength natural language processing in python.

Arora, A., Fiorino, H., Pellier, D., Métivier, M., and Pesty, S. (2018). A review of learning planning action models. The Knowledge Engineering Review, 33.

Botea, A., Muise, C., Agarwal, S., Alkan, O., Bajgar, O., Daly, E., Kishimoto, A., Lastras, L. A., Marinescu, R., Ondrej, J., Pedemonte, P., and Vodolán, M. (2019). Generating dialogue agents via automated planning. CoRR, abs/1902.00771.

Cimatti, A., Pistore, M., Roveri, M., and Traverso, P. (2003). Weak, strong, and strong cyclic planning via symbolic model checking. Artificial Intelligence, 147(1):35–84. Planning with Uncertainty and Incomplete Information.

DEEP-DIAL (2021). The fourth workshop on reasoning and learning for human-machine dialogues.

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.

Ghallab, M., Nau, D., and Traverso, P. (2004). Automated Planning: Theory and Practice. Elsevier Science.

Haslum, P., Lipovetzky, N., Magazzeni, D., Muise, C., Brachman, R., Rossi, F., and Stone, P. (2019). An introduction to the planning domain definition language, volume 13. Springer.

IBM (2024). O que é processamento de linguagem natural (pln)? Jurafsky, D. and Martin, J. H. (2021). Speech and Language Processing. Prentice Hall, 3rd edition.

Manly, B. F. and Alberto, J. A. N. (2016). Multivariate statistical methods: a primer. Chapman and Hall/CRC.

McDermott, D., Ghallab, M., Howe, A., Knoblock, C., Ram, A., Veloso, M., Weld, D., and Wilkins, D. (1998). Pddl - the planning domain definition language.

McTear, M. (2020). Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers.

Miglani, S. and Yorke-Smith, N. (2020). NLtoPDDL: One-shot learning of PDDL models from natural language process manuals. In Proceedings of the ICAPS Workshop on Knowledge Engineering for Planning and Scheduling (KEPS). ICAPS.

Nilsson, N. J. (1980). Principles of artificial intelligence. Tioga Publishing Co.

Pereira, S. d. L. and Barros, L. N. d. (2007). Planejamento sob incerteza para metas de alcançabilidade estendidas. 2007. Doutorado em ciência da computação, Instituto de Matemática e Estatística, Universidade de São Paulo, São Paulo.

Pinho, B. S. (2024). Planejamento não-determinístico para o gerenciamento de agentes de diálogos orientados à meta. Master’s thesis, Universidade Federal do Ceará.

Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2018). Improving language understanding with unsupervised learning. Technical Report.

Rauber, T. W. (2005). Redes neurais artificiais. 29.

Russell, S. and Norvig, P. (2009). Artificial Intelligence: A Modern Approach. Prentice Hall Press, USA, 3rd edition.

Segura-Muros, J. Á., Pérez, R., and Fernández-Olivares, J. (2021). Discovering relational and numerical expressions from plan traces for learning action models. Applied Intelligence, 51(11):7973–7989.

Shah, M. M. S., Chrpa, L., Jimoh, F., Kitchin, D. E., McCluskey, T. L., Parkinson, S., and Vallati, M. (2014). Knowledge engineering tools in planning : State-ofthe-art and future challenges.

Teixeira, M. S. and Dragoni, M. (2022). A review of plan-based approaches for dialogue management. Cogn. Comput., 14(3):1019–1038.

Teixeira, M. S., Dragoni, M., and Eccher, C. (2019). A planning strategy for dialogue management in healthcare. In SWH 2019 - Second International Workshop on Semantic Web Meets Health Data Management, pages 42–50.

Vallati, M. and Kitchin, D. (2020). Knowledge Engineering Tools and Techniques for AI Planning. Springer.