OYEN: A User-Centric LLM-Based Bilingual Healthcare Chatbot
Owen Chin, Nurul Syafidah Jamil, Zanariah Zainudin, Nor Azizah Hitam, Noraini Ibrahim, Ahmad Hakimi Ahmad Sa’ahiry · 2024
The expanding healthcare sector requires creative solutions to connect patients with vital information. Language barriers exacerbate the challenge, as many chatbots are predominantly English-based, limiting accessibility for non- English speakers. Therefore, this work introduces OYEN, a Large Language Model (LLM)-based chatbot designed for patients with bilingual (Mandarin and English) healthcare guidance. Early chatbot architectures relied on statistical Natural Language Processing (NLP) methods and keyword pattern recognition. However, the rise of LLMs with learning capabilities revolutionized chatbot development since 2018. Transformer-based LLMs became dominant due to their exceptional performance in modeling natural text. Developed for healthcare institutions in Malaysia offering Traditional Chinese Medicine (TCM) services, OYEN accurately responds to open-ended TCM-related questions. To ensure OYEN's capability to be user-language centric, responding in the language of the user's input (if a user inputs Mandarin, the response will be in Mandarin and vice versa for English language), a similarity search mechanism using a vector database which is known as Retrieval Augmented Generation (RAG) is integrated. This advanced technique enhances OYEN's ability to retrieve and present relevant TCM information.