Ila Ananta
ABSTRACT
Conversational agents have become extraordinarily popular over the last few years, with accelerated adoption due to COVID-19. Even though a lot of work has been done to devise a real-time agent very few of them focus on dynamic responses. The challenges for automatic medical diagnosis not only include issues for topic transition coherency and question understanding but also issues regarding the context of medical knowledge and symptoms of disease relations. In this paper, we propose a conversational agent that not only generates answers to specific medical questions but also makes more natural and human-like conversations and can adapt to the context and evolve over time. We propose an End-to-End knowledge-routed Relational Dialogue System that would incorporate a rich medical knowledge graph into the topic transition in dialogue management, and make it accommodative with NLU (Natural Language Understanding) and NLG (Natural Language Generation). A knowledge-routed graph for topic decision-making is used, which helps to identify relationships between symptoms and symptom-disease pairs. However, there are constraints on the extent of questions that knowledge graphs can address independently. To overcome these, we have used a fine-tuned GPT-3 model. While knowledge graphs organize data as interconnected entities, GPT-3 generates human-like text using learned patterns from large datasets. This approach enhances responses to intricate queries.
- [n. d.]. babylon-Symptom Checker. https://www.babylonhealth.com/en-us/what-we-offer/chatbot. Accessed: 2023-03-21.Google Scholar
- [n. d.]. Best practices for prompt engineering. https://medium.com/@saipragna.kancheti/best-practices-for-prompt-engineering-bf4117833371. Accessed: 2023-02-24.Google Scholar
- [n. d.]. Customizing GPT-3 for your application. https://openai.com/blog/customizing-gpt-3#exmple. Accessed: 2023-01-04.Google Scholar
- [n. d.]. Sensely an empathy-driven conversational platform. https://sensely.com/. Accessed: 2023-04-20.Google Scholar
- [n. d.]. The squad dataset. https://huggingface.co/datasets/squad. Accessed: 2023-01-14.Google Scholar
- Flora Amato, Stefano Marrone, Vincenzo Moscato, Gabriele Piantadosi, Antonio Picariello, Carlo Sansone, 2017. Chatbots Meet eHealth: Automatizing Healthcare.. In WAIAH@ AI* IA. 40–49.Google Scholar
- Qiming Bao, Lin Ni, and Jiamou Liu. 2020. HHH: an online medical chatbot system based on knowledge graph and hierarchical bi-directional attention. (2020), 1–10.Google Scholar
- RV Belfin, AJ Shobana, Megha Manilal, Ashly Ann Mathew, and Blessy Babu. 2019. A graph based chatbot for cancer patients. (2019), 717–721.Google Scholar
- Nivedita Bhirud, Subhash Tataale, Sayali Randive, and Shubham Nahar. 2019. A literature review on chatbots in healthcare domain. International journal of scientific & technology research 8, 7 (2019), 225–231.Google Scholar
- Gillian Cameron, David Cameron, Gavin Megaw, Raymond R Bond, Maurice Mulvenna, Siobhan O’Neill, Cherie Armour, and Michael McTear. 2018. Best practices for designing chatbots in mental healthcare–A case study on iHelpr. In British HCI Conference 2018. BCS Learning & Development Ltd.Google Scholar
- Ebrahim Elgazar. [n. d.]. Doctor’s Specialty Recommendation. https://www.kaggle.com/datasets/ebrahimelgazar/doctor-specialist-recommendation-system/versions/1?resource=download&select=Original_Dataset.csv. Accessed: 2023-02-4.Google Scholar
- Mlađan Jovanović, Marcos Baez, and Fabio Casati. 2020. Chatbots as conversational healthcare services. IEEE Internet Computing 25, 3 (2020), 44–51.Google ScholarDigital Library
- Tobias Kowatsch, Marcia Nißen, Chen-Hsuan I Shih, Dominik Rüegger, Dirk Volland, Andreas Filler, Florian Künzler, Filipe Barata, Sandy Hung, Dirk Büchter, 2017. Text-based healthcare chatbots supporting patient and health professional teams: preliminary results of a randomized controlled trial on childhood obesity. Persuasive Embodied Agents for Behavior Change (PEACH2017) (2017).Google Scholar
- Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019).Google Scholar
- Colm Sweeney, Courtney Potts, Edel Ennis, Raymond Bond, Maurice D Mulvenna, Siobhan O’neill, Martin Malcolm, Lauri Kuosmanen, Catrine Kostenius, Alex Vakaloudis, 2021. Can Chatbots help support a person’s mental health? Perceptions and views from mental healthcare professionals and experts. ACM Transactions on Computing for Healthcare 2, 3 (2021), 1–15.Google ScholarDigital Library
- Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuan-Jing Huang, Kam-Fai Wong, and Xiang Dai. 2018. Task-oriented dialogue system for automatic diagnosis. (2018), 201–207.Google Scholar
- Shayan Zamanirad, Boualem Benatallah, Carlos Rodriguez, Mohammadali Yaghoubzadehfard, Sara Bouguelia, and Hayet Brabra. 2020. State machine based human-bot conversation model and services. In International Conference on Advanced Information Systems Engineering. Springer, 199–214.Google ScholarDigital Library
- Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2019. Dialogpt: Large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536 (2019).Google Scholar
Recommendations
Response to a relational agent by hospital patients with depressive symptoms
Depression affects approximately 15% of the US population, and is recognized as an important risk factor for poor outcomes among patients with various illnesses. Automated health education and behavior change programs have the potential to help address ...
Photo-realistic conversation agent
Integrated image and graphics technologiesImage-based facial animation (IBFA) techniques allow us to build photorealistic talking heads. In this chapter, we address two important issues in creating a conversation agent using IBFA. First, we show how to make a conversation agent appear to be ...
Conversation quantisation for conversational knowledge process
I present an approach on conversational knowledge process based on conversation quantisation, which is a technique of approximating a continuous flow of conversation by a series of conversation quanta that represent points of the discourse. Conversation ...
Comments